Triple
T16393103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hyampolis |
E398103
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object |
Abae
Abae was an ancient town in Phocis, Greece, best known for its important oracle of Apollo and its role in various Greek historical and religious events.
|
E1212479
|
NE FINISHED |
How this triple was built (4 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: Abae | Statement: [Hyampolis, locatedNear, Abae]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Abae Context triple: [Hyampolis, locatedNear, Abae]
-
A.
Abui
Abui is a Papuan language spoken by the Abui people on Alor Island in eastern Indonesia, known for its complex verb morphology and typological interest.
-
B.
Awaba
Awaba is an Aboriginal name historically used for Lake Macquarie, a large coastal lake in New South Wales, Australia.
-
C.
Abur
Abur is the traditional name for the Old Permic alphabet, an early writing system used for the Komi language in the medieval Perm region of Russia.
-
D.
Azabu
Azabu is an upscale residential and entertainment district in central Tokyo known for its embassies, international community, and trendy dining and nightlife.
-
E.
Anbay
Anbay is an ancient South Arabian god associated with justice and oracles, venerated as a principal deity in the Qataban kingdom.
- 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: Abae Triple: [Hyampolis, locatedNear, Abae]
Generated description
Abae was an ancient town in Phocis, Greece, best known for its important oracle of Apollo and its role in various Greek historical and religious events.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Abae Target entity description: Abae was an ancient town in Phocis, Greece, best known for its important oracle of Apollo and its role in various Greek historical and religious events.
-
A.
Abui
Abui is a Papuan language spoken by the Abui people on Alor Island in eastern Indonesia, known for its complex verb morphology and typological interest.
-
B.
Awaba
Awaba is an Aboriginal name historically used for Lake Macquarie, a large coastal lake in New South Wales, Australia.
-
C.
Abur
Abur is the traditional name for the Old Permic alphabet, an early writing system used for the Komi language in the medieval Perm region of Russia.
-
D.
Azabu
Azabu is an upscale residential and entertainment district in central Tokyo known for its embassies, international community, and trendy dining and nightlife.
-
E.
Anbay
Anbay is an ancient South Arabian god associated with justice and oracles, venerated as a principal deity in the Qataban kingdom.
- F. None of above. chosen
Provenance (5 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_69d87f2880b48190ae1a9673a3bbef80 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e326447a7481909feac905edc707ec |
completed | April 18, 2026, 6:35 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a003c58280081908e4d73a75b09dbb8 |
completed | May 10, 2026, 8:05 a.m. |
| NEDg | Description generation | batch_6a0040d71e2c819084c106114e9c0de4 |
completed | May 10, 2026, 8:24 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0041cec01881909400e8c3874413e7 |
completed | May 10, 2026, 8:29 a.m. |
Created at: April 10, 2026, 5:08 a.m.