Triple
T26696624
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Petrolacosaurus kansensis |
E673038
|
entity |
| Predicate | hasTemporalFenestration |
P160467
|
FINISHED |
| Object | two lateral temporal openings |
—
|
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: two lateral temporal openings | Statement: [Petrolacosaurus kansensis, hasTemporalFenestration, two lateral temporal openings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTemporalFenestration Context triple: [Petrolacosaurus kansensis, hasTemporalFenestration, two lateral temporal openings]
-
A.
hasTemporalResolution
Indicates that one entity specifies the level of temporal detail or granularity at which another entity’s data, observation, or process is measured or represented.
-
B.
temporalFenestraCountPerSide
chosen
Indicates the number of temporal fenestra openings present on each side of the skull.
-
C.
hasTemporalBehavior
Indicates that an entity exhibits a particular pattern, characteristic, or change in behavior over time.
-
D.
hasTemporalUse
Indicates that something is used, applicable, or valid only during a specific time or temporal interval.
-
E.
hasTemporalClassification
Indicates a relationship where something is assigned or associated with a specific temporal category, period, or time-based classification.
- F. None of above.
Provenance (3 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_69eecda2b49c8190a6c481cfc4c07954 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f6afebd7ec8190ab696f363d84abf0 |
completed | May 3, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69f6aca204148190850a3dc325bc07b7 |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 27, 2026, 3:29 a.m.