Triple
T19875982
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Graham Greene |
E477636
|
entity |
| Predicate | participatedIn |
P149
|
FINISHED |
| Object | Maverick |
—
|
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: Maverick | Statement: [Graham Greene, participatedIn, Maverick]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Maverick Context triple: [Graham Greene, participatedIn, Maverick]
-
A.
Maverick
Maverick is a 1994 comedic Western film starring Mel Gibson, Jodie Foster, and James Garner, centered on a charming gambler trying to raise money for a high-stakes poker tournament.
-
B.
Maverick
Maverick is a cigarette brand known for its budget-friendly positioning within the U.S. tobacco market.
-
C.
Maverick
Maverick is the codename used by Chris Bradley, a minor Marvel Comics character associated with the X-Men universe who possesses mutant electrical powers.
-
D.
Maverick
Maverick is an entertainment company co-founded by Madonna that has operated in music, film, and artist management.
-
E.
Maverick
chosen
Maverick is a work by British novelist Graham Greene, likely reflecting his characteristic exploration of moral ambiguity and complex human motivations.
- 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_69d8e51f32b08190b3687f4f60353250 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e658db058c8190b7bf0b003ead5bfc |
completed | April 20, 2026, 4:48 p.m. |
Created at: April 10, 2026, 1:52 p.m.