Triple
T36732738
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ornitholestes |
E907383
|
entity |
| Predicate | likelyActivityPattern |
P119659
|
FINISHED |
| Object | active hunter |
—
|
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: active hunter | Statement: [Ornitholestes, likelyActivityPattern, active hunter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: likelyActivityPattern Context triple: [Ornitholestes, likelyActivityPattern, active hunter]
-
A.
likelySocialBehavior
Indicates that an entity is expected or predicted to engage in a particular social behavior or interaction.
-
B.
likelyBehavior
chosen
Indicates the behavior or action that an entity is expected or predicted to exhibit under given circumstances.
-
C.
likelyActiveDuring
Indicates that an entity is expected or inferred to be active or functioning during a specified time period or context.
-
D.
likelyLastActivity
Indicates that an activity is inferred to be the most recent or final action performed by an entity within a given context or timeframe.
-
E.
primaryActivityPattern
Indicates the main recurring type of activity or behavior that characterizes how an entity typically operates or functions.
- 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_69f76e75aa6881909b844d00a3888ee5 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f9fd6834cc8190aa27153d6a99f3bb |
completed | May 5, 2026, 2:23 p.m. |
| PD | Predicate disambiguation | batch_69f7cf7890008190a8bc355ff2d61c86 |
completed | May 3, 2026, 10:43 p.m. |
Created at: May 3, 2026, 4:12 p.m.