Triple
T27281415
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Homo antecessor |
E688340
|
entity |
| Predicate | evidenceOfBehavior |
P69361
|
FINISHED |
| Object | possible cannibalism |
—
|
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: possible cannibalism | Statement: [Homo antecessor, evidenceOfBehavior, possible cannibalism]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: evidenceOfBehavior Context triple: [Homo antecessor, evidenceOfBehavior, possible cannibalism]
-
A.
behaviorObserved
Indicates that a particular behavior or action has been witnessed, recorded, or detected in relation to an entity or context.
-
B.
evidenceOfActivity
chosen
Indicates that there is information or data supporting the occurrence or performance of a particular activity or action.
-
C.
behaviorNear
Indicates that one entity exhibits a behavior or action in close spatial proximity to another entity.
-
D.
affectsBehaviorOf
Indicates that one entity produces a change or influence on the behavior, actions, or conduct of another entity.
-
E.
behaviorCode
Indicates the specific rule, standard, or classification code that governs or characterizes an entity’s behavior in a given context.
- 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_69ef355998e08190bdff849e8f33adce |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f62cd2ceb481908cd9fae52a542206 |
completed | May 2, 2026, 4:56 p.m. |
| PD | Predicate disambiguation | batch_69f62c1762f881908c25e8f70ecd5041 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 11:07 a.m.