Triple
T2254135
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Koman languages |
E49680
|
entity |
| Predicate | haveProtoLanguage |
P2179
|
FINISHED |
| Object |
Proto-Koman
Proto-Koman is the reconstructed ancestral language from which the modern Koman languages of the Nilo-Saharan family are derived.
|
E247233
|
NE FINISHED |
How this triple was built (5 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Proto-Koman | Statement: [Koman languages, haveProtoLanguage, Proto-Koman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Proto-Koman Context triple: [Koman languages, haveProtoLanguage, Proto-Koman]
-
A.
Proto-Barito
Proto-Barito is the reconstructed ancestral language from which the Barito subgroup of Austronesian languages is derived.
-
B.
Proto-Turkic
Proto-Turkic is the reconstructed common ancestor language of all Turkic languages, from which branches like Southwestern Turkic later evolved.
-
C.
Proto-Tyrsenian
Proto-Tyrsenian is the hypothesized common ancestor language of the Tyrsenian family, believed to underlie languages such as Lemnian and Etruscan in the ancient Mediterranean region.
-
D.
Scythian languages
Scythian languages are an extinct group of ancient Eastern Iranian languages once spoken by the nomadic Scythian peoples across the Eurasian steppe.
-
E.
Palaic
Palaic is an extinct Anatolian Indo-European language once spoken in north-central Anatolia, known primarily from limited cuneiform texts.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Proto-Koman Triple: [Koman languages, haveProtoLanguage, Proto-Koman]
Generated description
Proto-Koman is the reconstructed ancestral language from which the modern Koman languages of the Nilo-Saharan family are derived.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Proto-Koman Target entity description: Proto-Koman is the reconstructed ancestral language from which the modern Koman languages of the Nilo-Saharan family are derived.
-
A.
Proto-Barito
Proto-Barito is the reconstructed ancestral language from which the Barito subgroup of Austronesian languages is derived.
-
B.
Proto-Turkic
Proto-Turkic is the reconstructed common ancestor language of all Turkic languages, from which branches like Southwestern Turkic later evolved.
-
C.
Proto-Tyrsenian
Proto-Tyrsenian is the hypothesized common ancestor language of the Tyrsenian family, believed to underlie languages such as Lemnian and Etruscan in the ancient Mediterranean region.
-
D.
Scythian languages
Scythian languages are an extinct group of ancient Eastern Iranian languages once spoken by the nomadic Scythian peoples across the Eurasian steppe.
-
E.
Palaic
Palaic is an extinct Anatolian Indo-European language once spoken in north-central Anatolia, known primarily from limited cuneiform texts.
- F. None of above. chosen
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: haveProtoLanguage Context triple: [Koman languages, haveProtoLanguage, Proto-Koman]
-
A.
hasProtoLanguage
chosen
Indicates that a language or language family originates from, or is derived from, a specified proto-language.
-
B.
hasLanguageOn
Indicates that an entity uses or is associated with a particular language in a specific context, medium, or location.
-
C.
hasLanguageRepresentation
Indicates that an entity is expressed, encoded, or represented using a particular natural or formal language.
-
D.
hasLanguages
Indicates that an entity is associated with one or more languages it uses, supports, or is expressed in.
-
E.
hasSignificantLanguage
Indicates that an entity possesses a language that plays an important or primary role in its communication, identity, or functioning.
- F. None of above.
Provenance (6 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69a88aaa9250819095e127d0d77e8a32 |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc12029548190af9f2cdd7a4de2d6 |
completed | March 7, 2026, 6:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae6b1dd6fc8190bd762fb3a17258b0 |
completed | March 9, 2026, 6:39 a.m. |
| NEDg | Description generation | batch_69ae6bbdef14819084b96389435ca080 |
completed | March 9, 2026, 6:42 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ae6c2cfac48190b0425088e79cd122 |
completed | March 9, 2026, 6:43 a.m. |
| PD | Predicate disambiguation | batch_69abbdb34c148190b51e99f540f97204 |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:47 p.m.