Triple
T36846814
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amelia Earhart’s Lockheed Electra 10E |
E910570
|
entity |
| Predicate | lastDepartureAirport |
P96207
|
FINISHED |
| Object | Lae Airfield |
—
|
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: Lae Airfield | Statement: [Amelia Earhart’s Lockheed Electra 10E, lastDepartureAirport, Lae Airfield]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lastDepartureAirport Context triple: [Amelia Earhart’s Lockheed Electra 10E, lastDepartureAirport, Lae Airfield]
-
A.
destinationAirportICAO
Indicates the airport, identified by its ICAO code, that serves as the destination in a flight or travel-related context.
-
B.
previousAirportName
Indicates the name that an airport was known by before its current name.
-
C.
lastFlightLandingSite
Indicates the location where an entity’s most recent flight concluded and landed.
-
D.
originAirportOnFinalFlight
chosen
Indicates the airport from which an entity’s final recorded flight departs.
-
E.
originAirportICAO
Indicates the airport, identified by its ICAO code, from which a flight or journey departs.
- 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_69f9fd6834cc8190aa27153d6a99f3bb |
completed | May 5, 2026, 2:23 p.m. |
| PD | Predicate disambiguation | batch_69f7cf7890008190a8bc355ff2d61c86 |
completed | May 3, 2026, 10:43 p.m. |
Created at: May 3, 2026, 4:13 p.m.