Triple
T23821691
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USS Cole (DDG-67) |
E589253
|
entity |
| Predicate | woundedInAttack |
P28646
|
FINISHED |
| Object | dozens of sailors |
—
|
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: dozens of sailors | Statement: [USS Cole (DDG-67), woundedInAttack, dozens of sailors]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: woundedInAttack Context triple: [USS Cole (DDG-67), woundedInAttack, dozens of sailors]
-
A.
woundedAt
Indicates that an entity was injured or harmed at a specific place or during a particular event.
-
B.
wasWoundedIn
chosen
Indicates that an entity sustained an injury as a result of a specified event, situation, or conflict.
-
C.
firstWoundInflictedBy
Indicates that the referenced wound is the earliest (chronologically first) injury inflicted by the specified agent on the specified target.
-
D.
actedDespiteWounds
Indicates that an entity performed an action or fulfilled a role even though it was wounded or injured at the time.
-
E.
bodyPartAttacked
Indicates that a specific body part of an entity is the target or focus of an attack.
- 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_69e25d18619081909c7fb89d8926f14a |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c7af4d4481908095348fae9e54f4 |
completed | April 29, 2026, 8:56 a.m. |
| PD | Predicate disambiguation | batch_69f156036ad48190bc2ffdaf39218bcb |
completed | April 29, 2026, 12:51 a.m. |
Created at: April 17, 2026, 7:59 p.m.