Triple
T21708872
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fury (tank) |
E535844
|
entity |
| Predicate | crewCasualtiesInFiction |
P29707
|
FINISHED |
| Object | most of crew killed in final battle |
—
|
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: most of crew killed in final battle | Statement: [Fury (tank), crewCasualtiesInFiction, most of crew killed in final battle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: crewCasualtiesInFiction Context triple: [Fury (tank), crewCasualtiesInFiction, most of crew killed in final battle]
-
A.
deathInFiction
Indicates that an entity’s death occurs within a fictional work or narrative rather than in real life.
-
B.
crewFatality
chosen
Indicates that one or more members of a crew have died as a result of the related event or situation.
-
C.
livesInFiction
Indicates that one entity exists or resides within the fictional world or narrative setting created by another entity.
-
D.
deathTypeInFiction
Indicates the manner or category of how a character dies within a fictional narrative.
-
E.
worksInFictionalContext
Indicates that an entity performs work or fulfills a role within a fictional or imagined setting rather than in real-world circumstances.
- 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_69e0c46b44c0819088ab883ebd44e0e8 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69efb5314a288190b4b8347cca15aaa8 |
completed | April 27, 2026, 7:12 p.m. |
| PD | Predicate disambiguation | batch_69e6969113cc8190ab69855ef5667e4b |
completed | April 20, 2026, 9:11 p.m. |
Created at: April 16, 2026, 6:46 p.m.