Triple
T21652055
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Therapsids |
E534361
|
entity |
| Predicate | jawEvolution |
P144872
|
FINISHED |
| Object | trend from multiple jaw bones to single dentary bone |
—
|
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: trend from multiple jaw bones to single dentary bone | Statement: [Therapsids, jawEvolution, trend from multiple jaw bones to single dentary bone]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: jawEvolution Context triple: [Therapsids, jawEvolution, trend from multiple jaw bones to single dentary bone]
-
A.
jawType
Indicates the specific kind or classification of jaw structure associated with an entity.
-
B.
jawMechanics
Indicates the functional relationship between jaw structure and its movements or forces during actions like biting, chewing, or speaking.
-
C.
jawFunction
Indicates the functional role, movement, or mechanical action performed by a jaw in relation to other anatomical structures or processes.
-
D.
hasJaw
Indicates that one entity possesses or is equipped with a jaw as a physical anatomical feature.
-
E.
isJawless
Indicates that an entity lacks a jaw or does not possess a true jaw structure.
- 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_69e0c466aec88190ba39c7543dbc8ba2 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef591594a08190bf0ddd0a0c0922ba |
completed | April 27, 2026, 12:39 p.m. |
| PD | Predicate disambiguation | batch_69e696826c3c81909270791e79760937 |
completed | April 20, 2026, 9:11 p.m. |
| PDg | Predicate description generation | batch_69e69b4aa2b48190830107391e81571a |
completed | April 20, 2026, 9:31 p.m. |
Created at: April 16, 2026, 6:36 p.m.