Triple
T38602011
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blackburn Shark |
E934239
|
entity |
| Predicate | successorRoleAircraft |
P203089
|
FINISHED |
| Object | Fairey Swordfish |
—
|
NE NERFINISHED |
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: Fairey Swordfish | Statement: [Blackburn Shark, successorRoleAircraft, Fairey Swordfish]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: successorRoleAircraft Context triple: [Blackburn Shark, successorRoleAircraft, Fairey Swordfish]
-
A.
successorAircraft
Indicates that one aircraft model directly follows and replaces another in a developmental or operational sequence.
-
B.
successorAircraftType
Indicates that one aircraft type directly follows and replaces another in operational or developmental succession.
-
C.
successorAircraftProgram
Indicates that one aircraft program directly follows and replaces another as its successor in development or service.
-
D.
predecessorAircraft
Indicates that one aircraft model directly precedes another in a developmental or generational sequence.
-
E.
successorRoleShip
Indicates that one role succeeds or takes over from another role in a sequence or hierarchy.
- F. None of above. chosen
Provenance (4 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_69f76ecc17688190b389b693a5927501 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a011e5a419081908d06a07b395ebd97 |
completed | May 11, 2026, 12:10 a.m. |
| PD | Predicate disambiguation | batch_6a011de119048190b27d361cffabc228 |
completed | May 11, 2026, 12:08 a.m. |
| PDg | Predicate description generation | batch_6a011e599cd081909687a314f8d1895b |
completed | May 11, 2026, 12:10 a.m. |
Created at: May 3, 2026, 4:32 p.m.