Triple
T20236830
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jill Arlyn Oppenheim |
E498170
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Tony Rome |
—
|
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: Tony Rome | Statement: [Jill Arlyn Oppenheim, notableWork, Tony Rome]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tony Rome Context triple: [Jill Arlyn Oppenheim, notableWork, Tony Rome]
-
A.
Tony Rome
chosen
Tony Rome is a 1967 neo-noir detective film starring Frank Sinatra as a hard-boiled private investigator in Miami.
-
B.
Corky Romano
Corky Romano is a 2001 slapstick crime-comedy film about an inept veterinarian who goes undercover in the FBI to help his mob family.
-
C.
Tony Palermo
Tony Palermo is an American drummer best known for his work with the rock band Papa Roach.
-
D.
Tony Lombardo
Tony Lombardo is a film editor known for his work on the comedy movie "Van Wilder."
-
E.
Lou Romano
Lou Romano is an American animator, art director, and voice actor best known for his work with Pixar, including voicing the character Alfredo Linguini in the film "Ratatouille."
- 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_69da6274c58c81909c646eabed6f4f30 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6716a5af0819095ea419a4d1f0d1d |
completed | April 20, 2026, 6:33 p.m. |
Created at: April 11, 2026, 11:40 p.m.