Triple
T35835551
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bessie Coleman |
E1035923
|
entity |
| Predicate | placeOfPilotTraining |
P87281
|
FINISHED |
| Object | France |
—
|
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: France | Statement: [Bessie Coleman, placeOfPilotTraining, France]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: placeOfPilotTraining Context triple: [Bessie Coleman, placeOfPilotTraining, France]
-
A.
hasFlightTrainingFacility
Indicates that an entity provides or hosts a facility where flight training or pilot instruction is conducted.
-
B.
hasFlightTrainingActivity
Indicates that an entity is involved in or associated with a flight training activity.
-
C.
tookFlightTrainingIn
chosen
Indicates that an entity received or completed flight training at or through a specified organization, location, or program.
-
D.
aircraftTrainedOn
Indicates that an aircraft has been used as the platform or subject for training a person or crew in its operation or related skills.
-
E.
aviationLicense
Indicates that an entity holds an official authorization or certification to operate aircraft in aviation activities.
- 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_69f76e192a94819082db360cb91e6a8d |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fd6f9d600c8190acf495b7fc632e4b |
completed | May 8, 2026, 5:07 a.m. |
| PD | Predicate disambiguation | batch_69fd6e98a2948190a9f78c415ad23b8c |
completed | May 8, 2026, 5:03 a.m. |
Created at: May 3, 2026, 4:06 p.m.