Triple
T2464027
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle off Samar |
E55200
|
entity |
| Predicate | U.S.ShipsInvolved |
P680
|
FINISHED |
| Object | escort carriers |
—
|
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: escort carriers | Statement: [Battle off Samar, U.S.ShipsInvolved, escort carriers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: U.S.ShipsInvolved Context triple: [Battle off Samar, U.S.ShipsInvolved, escort carriers]
-
A.
involvedShipUnitedStates
chosen
Indicates that a ship involved in an event, action, or relationship is associated with or belongs to the United States.
-
B.
numberOfShipsInvolved
Indicates the total count of ships that participated or were involved in a specified event or situation.
-
C.
aircraftCarrierInvolved
Indicates that an aircraft carrier participates in, is present at, or is otherwise directly involved in the specified event or situation.
-
D.
involvedShipJapan
Indicates that a ship associated with Japan was involved in the referenced event or activity.
-
E.
navalVesselsAlliedApprox
Indicates that two or more naval vessels are approximately allied, suggesting a cooperative or friendly relationship without specifying a precise or formal alliance.
- 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_69ab49e3622c8190ad22afa2c4fbb807 |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abd2bc7b5481908b3664495e99f1a4 |
completed | March 7, 2026, 7:24 a.m. |
| PD | Predicate disambiguation | batch_69abd0b3ea308190a6d8499c2a542c50 |
completed | March 7, 2026, 7:16 a.m. |
Created at: March 6, 2026, 9:44 p.m.