Triple
T37667202
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USS Hoel (DD-533) |
E937852
|
entity |
| Predicate | lostCrew |
P29707
|
FINISHED |
| Object | over half of crew killed or missing in sinking |
—
|
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: over half of crew killed or missing in sinking | Statement: [USS Hoel (DD-533), lostCrew, over half of crew killed or missing in sinking]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lostCrew Context triple: [USS Hoel (DD-533), lostCrew, over half of crew killed or missing in sinking]
-
A.
crewFatality
chosen
Indicates that one or more members of a crew have died as a result of the related event or situation.
-
B.
crewComplementAtSinking
Indicates the number or composition of a vessel’s crew present on board at the time it sank.
-
C.
fatalitiesOnboard
Indicates that the relationship specifies the number of people who died among those present on a particular vehicle or craft.
-
D.
crewOnboard
Indicates that a person or group is serving as crew aboard a specific vehicle, vessel, or craft.
-
E.
passengersAtTimeOfDestruction
Indicates that the specified passengers were present on or associated with the entity (e.g., a vehicle or vessel) at the moment it was destroyed.
- 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_69f76ed6df7c8190b018e5baea716ceb |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fba9e27d0c81908342e28f016d221a |
completed | May 6, 2026, 8:51 p.m. |
| PD | Predicate disambiguation | batch_69fba887821c8190ae93ef1dd389e9c8 |
completed | May 6, 2026, 8:45 p.m. |
Created at: May 3, 2026, 4:18 p.m.