Triple
T4208593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Air France Flight 447 |
E93840
|
entity |
| Predicate | intendedArrivalDateLocal |
P32352
|
FINISHED |
| Object | 2009-06-01 morning |
—
|
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: 2009-06-01 morning | Statement: [Air France Flight 447, intendedArrivalDateLocal, 2009-06-01 morning]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: intendedArrivalDateLocal Context triple: [Air France Flight 447, intendedArrivalDateLocal, 2009-06-01 morning]
-
A.
arrivalDatePlanned
chosen
Indicates the date on which an arrival is scheduled or expected to occur according to a plan.
-
B.
arrivalAt
Indicates the event or state of an entity reaching and being present at a specific destination or location.
-
C.
estimatedArrivalInAustralia
Indicates the expected date and/or time when an entity is predicted to arrive in Australia.
-
D.
dateOfDisembarkation
Indicates the specific date on which an individual or entity got off or was released from a vehicle, vessel, or mode of transport.
-
E.
deliveryDate
Indicates the specific date on which a product, service, or item is scheduled or expected to be delivered.
- 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.