Triple
T20942837
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Half Past Dead |
E515765
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Tony Plana |
—
|
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 Plana | Statement: [Half Past Dead, starring, Tony Plana]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tony Plana Context triple: [Half Past Dead, starring, Tony Plana]
-
A.
Tony Plana
chosen
Tony Plana is a Cuban-American actor and director best known for his role as Ignacio Suarez on the television series "Ugly Betty."
-
B.
Tony Almeida
Tony Almeida is a key fictional Counter Terrorist Unit agent in the television series "24," known for his complex loyalties and evolving role across multiple seasons.
-
C.
John Platania
John Platania is an American guitarist and session musician best known for his long-time collaboration with Van Morrison and his distinctive work on several classic rock and folk-rock recordings.
-
D.
Tony de Zarraga
Tony de Zarraga is a film editor best known for his work on the 1984 romantic drama "Bolero."
-
E.
Jo Lupo
Jo Lupo is a tough, highly skilled former U.S. Army Ranger who serves as the no-nonsense deputy sheriff in the quirky, science-driven town of Eureka on the TV series "Eureka."
- 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_69e0b4fc13408190b06868df03c5c29b |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6f9571c448190b314a66e02772b1e |
completed | April 21, 2026, 4:13 a.m. |
Created at: April 16, 2026, 12:50 p.m.