Triple
T23525198
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Vernon |
E574612
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Topaz |
—
|
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: Topaz | Statement: [John Vernon, notableWork, Topaz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Topaz Context triple: [John Vernon, notableWork, Topaz]
-
A.
Topaz
Topaz is a silicate mineral gemstone prized for its clarity and range of colors, commonly used in jewelry and often linked to themes of strength and protection.
-
B.
Topaz
chosen
Topaz is a 1969 Cold War espionage thriller film directed by Alfred Hitchcock, based on the novel by Leon Uris.
-
C.
Topaz
Topaz is the unusual middle name of William McGonagall, the Scottish poet often cited as one of the worst in the English language.
-
D.
Topaz
Topaz is a formidable warrior and enforcer who serves the Grandmaster on the planet Sakaar in the Marvel Cinematic Universe.
-
E.
Topaze
Topaze is a celebrated French play by Marcel Pagnol that satirizes corruption and moral compromise through the story of an idealistic schoolteacher drawn into the world of politics and business.
- 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_69e245bb3dcc8190ba9a2b35972b58d0 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1ac72bfb88190b7da3837e66e851c |
completed | April 29, 2026, 7 a.m. |
Created at: April 17, 2026, 6:09 p.m.