Triple
T36846873
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NR16020 |
E910571
|
entity |
| Predicate | lastKnownFlightLeg |
P186579
|
FINISHED |
| Object | Lae to Howland Island |
—
|
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: Lae to Howland Island | Statement: [NR16020, lastKnownFlightLeg, Lae to Howland Island]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lastKnownFlightLeg Context triple: [NR16020, lastKnownFlightLeg, Lae to Howland Island]
-
A.
lastKnownLeg
chosen
Indicates the most recent or final leg (segment) in a sequence of legs associated with an entity or journey.
-
B.
lastFlight
Indicates that one flight is the final or most recent flight taken or operated by a given entity within a specified context or sequence.
-
C.
lastFlightWith
Indicates that one flight is the most recent flight taken by or associated with a given entity in relation to another entity or context.
-
D.
lastFlightDesignation
Indicates the specific flight identifier assigned to the most recent flight associated with an entity.
-
E.
finalFlightNumber
Indicates the flight number assigned to the last or concluding segment of a journey or itinerary.
- 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_69f76e7f65a881908651b702da592b6d |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb563aec448190875410fb1a3ed624 |
completed | May 6, 2026, 2:54 p.m. |
| PD | Predicate disambiguation | batch_69fb35b9ede881908aaae93a215525df |
completed | May 6, 2026, 12:36 p.m. |
Created at: May 3, 2026, 4:13 p.m.