Triple
T25342007
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Korean Air Lines Flight 007 shootdown |
E635436
|
entity |
| Predicate | interceptingPilot |
P133688
|
FINISHED |
| Object | Gennadi Osipovich |
—
|
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: Gennadi Osipovich | Statement: [Korean Air Lines Flight 007 shootdown, interceptingPilot, Gennadi Osipovich]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: interceptingPilot Context triple: [Korean Air Lines Flight 007 shootdown, interceptingPilot, Gennadi Osipovich]
-
A.
pilotHijacker
Indicates that the subject is a pilot who hijacks, or has hijacked, an aircraft.
-
B.
interceptedBy
Indicates that an action, communication, or movement is stopped, captured, or diverted by another agent before reaching its intended target or destination.
-
C.
pilotFor
chosen
Indicates that one entity serves as the pilot operating or navigating a vehicle, aircraft, or vessel on behalf of another entity (such as an organization, mission, or owner).
-
D.
interceptingPlayer
Indicates that one player takes possession of or disrupts a pass, throw, or transmission intended for another player or target.
-
E.
interceptRepresents
Indicates that one entity acts as a representation or model of the interception of another entity or process.
- 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_69e75a99bd6481909476115b35b9a8e4 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f621fcea1481909b6f8b3af1ee6820 |
completed | May 2, 2026, 4:10 p.m. |
| PD | Predicate disambiguation | batch_69f620dc38088190b56b2b15ed75b3c2 |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 21, 2026, 1:32 p.m.