Triple
T15004779
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sentinelese people |
E377679
|
entity |
| Predicate | responseToIntrusion |
P116322
|
FINISHED |
| Object | often hostile |
—
|
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: often hostile | Statement: [Sentinelese people, responseToIntrusion, often hostile]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: responseToIntrusion Context triple: [Sentinelese people, responseToIntrusion, often hostile]
-
A.
countermeasuresFaced
Indicates that one entity has encountered or had to deal with countermeasures implemented by another entity.
-
B.
responseToAbuse
Indicates a reaction, behavior, or measure taken by one party in consequence of abusive actions or treatment from another.
-
C.
attackOccurred
Indicates that an act of aggression or violence was carried out by one party against another.
-
D.
lawEnforcementResponse
Indicates the actions or measures taken by law enforcement agencies in reaction to an incident, behavior, or situation.
-
E.
threatenedResponse
Indicates that one entity performs or communicates a response as a result of being threatened by another entity or situation.
- 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_69d85cd3a3c881908c71fc424d459c17 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded7322b5c81909089cbbf816e1436 |
completed | April 15, 2026, 12:09 a.m. |
| PD | Predicate disambiguation | batch_69de9a6531a88190acde65199a477350 |
completed | April 14, 2026, 7:49 p.m. |
| PDg | Predicate description generation | batch_69deb1a88d588190996afa8e5b32b552 |
completed | April 14, 2026, 9:29 p.m. |
Created at: April 10, 2026, 2:54 a.m.