Triple
T4208609
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Air France Flight 447 |
E93840
|
entity |
| Predicate | wreckageRecovery |
P30695
|
FINISHED |
| Object | underwater search operation |
—
|
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: underwater search operation | Statement: [Air France Flight 447, wreckageRecovery, underwater search operation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wreckageRecovery Context triple: [Air France Flight 447, wreckageRecovery, underwater search operation]
-
A.
wreckSalvaged
Indicates that a previously wrecked object or structure has been recovered or salvaged from its damaged or sunken state.
-
B.
wreckDiscovery
Indicates that an entity discovers, finds, or identifies a wreck (such as a ruined or destroyed object, vehicle, or structure).
-
C.
containsWreck
Indicates that one entity includes or holds within it the remains or wreckage of another entity.
-
D.
debrisRecoveryEffort
chosen
Indicates efforts or actions undertaken to locate, collect, and secure debris resulting from an incident or event.
-
E.
shipwreckUse
Indicates that an entity makes use of, interacts with, or derives benefit from a shipwreck.
- 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_69b3451743608190808f41d17ccf2650 |
completed | March 12, 2026, 10:58 p.m. |
| NER | Named-entity recognition | batch_69b34e098da881909a0cc339cc186627 |
completed | March 12, 2026, 11:36 p.m. |
| PD | Predicate disambiguation | batch_69b347efd9b08190bb50f82e4e7fe06d |
completed | March 12, 2026, 11:10 p.m. |
Created at: March 12, 2026, 11:03 p.m.