Triple
T20160932
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pushing Tin |
E491699
|
entity |
| Predicate | editedBy |
P1954
|
FINISHED |
| Object | Jon Gregory |
—
|
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: Jon Gregory | Statement: [Pushing Tin, editedBy, Jon Gregory]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jon Gregory Context triple: [Pushing Tin, editedBy, Jon Gregory]
-
A.
Jon Gregory
chosen
Jon Gregory was a British film editor known for his work on acclaimed films such as "Four Weddings and a Funeral," "Secrets & Lies," and several collaborations with director Mike Leigh.
-
B.
Allen Gregory
Allen Gregory is an animated television sitcom that follows an overconfident, precocious seven-year-old boy navigating the challenges of attending public school.
-
C.
Gregory Jarvis
Gregory Jarvis was an American engineer and astronaut who served as a payload specialist on the ill-fated Space Shuttle Challenger mission STS-51-L.
-
D.
David Gregory
David Gregory is an American television journalist best known for serving as the moderator of NBC’s long-running news program "Meet the Press."
-
E.
Gregory Bald
Gregory Bald is a scenic grassy summit in the Great Smoky Mountains renowned for its panoramic views and spectacular flame azalea displays.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69da6266c6888190bc1a3ecf24814d34 |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e667e43940819080f6a0b7331aaab0 |
completed | April 20, 2026, 5:52 p.m. |
Created at: April 11, 2026, 11:34 p.m.