Triple
T16873052
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David H. Franzoni |
E421222
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Amistad |
E178791
|
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: Amistad | Statement: [David H. Franzoni, notableWork, Amistad]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Amistad Context triple: [David H. Franzoni, notableWork, Amistad]
-
A.
Amistad
chosen
Amistad is a 1997 historical drama film directed by Steven Spielberg that depicts the true story of a revolt by enslaved Africans aboard the Spanish ship La Amistad and the subsequent legal battle in the United States.
-
B.
Cinqué in Amistad
Cinqué in *Amistad* is the central historical figure and leader of the enslaved Africans who revolt against their captors in Steven Spielberg’s 1997 film.
-
C.
Verdão
Verdão is the popular nickname of Sociedade Esportiva Palmeiras, one of Brazil’s most successful and traditional football clubs.
-
D.
Glory
Glory is the airline callsign used by UNI Air, a Taiwanese regional carrier.
-
E.
Glory
Glory is a feminine given name most notably associated with American professional basketball player Glory Johnson.
- 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_69d889d470fc8190b4aec199636c0c56 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e3b7f40410819088db22fa0d1eb808 |
completed | April 18, 2026, 4:57 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00c2b0dcbc8190a164cbd57586ac9c |
completed | May 10, 2026, 5:38 p.m. |
Created at: April 10, 2026, 5:29 a.m.