Triple
T13796621
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Die Hard 2 |
E331532
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Dennis Franz |
E93505
|
NE FINISHED |
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: Dennis Franz | Statement: [Die Hard 2, starring, Dennis Franz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dennis Franz Context triple: [Die Hard 2, starring, Dennis Franz]
-
A.
Dennis Franz
chosen
Dennis Franz is an American actor best known for his acclaimed portrayal of Detective Andy Sipowicz on the television series "NYPD Blue."
-
B.
William Katt
William Katt is an American actor best known for starring in the 1980s television series "The Greatest American Hero" and appearing in films such as "Carrie."
-
C.
Colin Ferguson
Colin Ferguson is a Canadian-American actor best known for starring as Sheriff Jack Carter on the science fiction television series "Eureka."
-
D.
Dennis Farina
Dennis Farina was an American actor and former Chicago police officer best known for his tough-guy roles in films like "Get Shorty" and on TV series such as "Law & Order."
-
E.
Mike Farrell
Mike Farrell is an American actor, producer, and activist best known for his role as Captain B.J. Hunnicutt on the television series M*A*S*H.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d81c58feb08190a77bca8bf7d6d20f |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de025be1f08190aac525d72d7dc0c3 |
completed | April 14, 2026, 9:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7b8d893448190b37ecbf8d2ded239 |
completed | May 3, 2026, 9:06 p.m. |
Created at: April 9, 2026, 10:11 p.m.