Triple
T16809969
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | B. A. Baracus |
E408581
|
entity |
| Predicate | createdBy |
P806
|
FINISHED |
| Object | Frank Lupo |
E856644
|
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: Frank Lupo | Statement: [B. A. Baracus, createdBy, Frank Lupo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frank Lupo Context triple: [B. A. Baracus, createdBy, Frank Lupo]
-
A.
Frank Lupo
chosen
Frank Lupo was an American television writer and producer best known for co-creating popular 1980s action series such as The A-Team and Hunter.
-
B.
Frank Laico
Frank Laico was an American recording engineer renowned for his work at Columbia Records, where he helped shape the sound of landmark jazz and popular music albums in the mid-20th century.
-
C.
Leo Trombetta
Leo Trombetta is a film editor best known for his work on acclaimed movies such as "Little Children."
-
D.
Louis Falco
Louis Falco was an American modern dancer and choreographer known for his innovative work in contemporary dance and for choreographing the film "Fame."
-
E.
Frank Giordano
Frank Giordano was a criminal defendant in the notable U.S. Supreme Court case United States v. Giordano, which addressed the legality of certain federal wiretap authorizations.
- 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_69d88393905081908d00a86b99996ac8 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3b2cf680c8190bcd640570c524918 |
completed | April 18, 2026, 4:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a012327b68881908ad5f4e2fe03f56a |
completed | May 11, 2026, 12:30 a.m. |
Created at: April 10, 2026, 5:23 a.m.