Triple
T4208604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Air France Flight 447 |
E93840
|
entity |
| Predicate | blackBoxesRecovered |
P47673
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Air France Flight 447, blackBoxesRecovered, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: blackBoxesRecovered Context triple: [Air France Flight 447, blackBoxesRecovered, yes]
-
A.
recoveredIn
Indicates that something lost, damaged, or impaired has been restored or regained within a particular context, process, or location.
-
B.
remainsRecoveredFrom
chosen
Indicates that physical remains of an entity have been found and retrieved from a specified source, location, or context.
-
C.
numberOfBonesRecovered
Indicates the count of bones that have been found and recovered in relation to a particular subject or event.
-
D.
recoveredFrom
Indicates that an entity has returned to a normal or improved state after previously experiencing or being affected by another specified condition, event, or problem.
-
E.
partiallyRecapturedBy
Indicates that an entity that was previously captured or controlled has been regained only in part by another entity, not fully restored to its prior captured state.
- 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.