Triple
T3124486
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lars Johanson |
E65263
|
entity |
| Predicate | positionOnAltaicHypothesis |
P45508
|
FINISHED |
| Object | critical |
—
|
LITERAL FINISHED |
How this triple was built (2 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: critical | Statement: [Lars Johanson, positionOnAltaicHypothesis, critical]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionOnAltaicHypothesis Context triple: [Lars Johanson, positionOnAltaicHypothesis, critical]
-
A.
ancientLanguageFamily
Indicates that one language belongs to or descends from a historically ancient family of related languages.
-
B.
identifiedAsIndoEuropeanBy
Indicates that an entity has been classified or recognized as Indo-European by a specified source or agent.
-
C.
areAgglutinativeLanguages
Indicates that the related languages primarily form words by stringing together distinct morphemes, each carrying a specific grammatical meaning, in a clear and segmentable way.
-
D.
languageFamilyPosition
Indicates the hierarchical position or role that a language occupies within its broader language family structure.
-
E.
hasLinguisticTypology
Indicates a relationship where a language or linguistic system is characterized by a specific typological classification or structural type.
- F. None of above. chosen
Provenance (4 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_69ad8580c72481909672d37acf647893 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada52d856c8190a5d65b8a6452be21 |
completed | March 8, 2026, 4:34 p.m. |
| PD | Predicate disambiguation | batch_69ad9df62e548190b053e1478deed467 |
completed | March 8, 2026, 4:04 p.m. |
| PDg | Predicate description generation | batch_69ada0f7c21c819087e9992f5fe30a37 |
completed | March 8, 2026, 4:16 p.m. |
Created at: March 8, 2026, 3:04 p.m.