Triple
T2489730
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HMS Exeter |
E52009
|
entity |
| Predicate | crewStatusAfterSinking |
P35576
|
FINISHED |
| Object | many survivors taken prisoner by Japanese forces |
—
|
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: many survivors taken prisoner by Japanese forces | Statement: [HMS Exeter, crewStatusAfterSinking, many survivors taken prisoner by Japanese forces]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: crewStatusAfterSinking Context triple: [HMS Exeter, crewStatusAfterSinking, many survivors taken prisoner by Japanese forces]
-
A.
survivorsWhenSunk
chosen
Indicates that when an entity (such as a vessel) was sunk, there were survivors from that event.
-
B.
sunkDuring
Indicates that one entity was sunk in the course of, or as a result of, the event or time period represented by another entity.
-
C.
opposingForcesAtSinking
Indicates that two or more forces are acting in opposition to each other at the time or location of a sinking event.
-
D.
sunkBy
Indicates that one entity (typically a vessel or structure) was caused to sink or be destroyed in water by another entity.
-
E.
shipsSunkOrTotalLoss
Indicates that the referenced ships were sunk or otherwise rendered a total loss (permanently unusable).
- 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_69ab4955111c8190835bf619adec21ff |
completed | March 6, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69abd17b7a048190bcc8f0a66514a052 |
completed | March 7, 2026, 7:19 a.m. |
| PD | Predicate disambiguation | batch_69abd0b980b481908d4932bcea4a6167 |
completed | March 7, 2026, 7:16 a.m. |
Created at: March 6, 2026, 9:45 p.m.