Triple
T13393890
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Franco Interlenghi |
E319647
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Shoeshine |
E626390
|
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: Shoeshine | Statement: [Franco Interlenghi, notableWork, Shoeshine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shoeshine Context triple: [Franco Interlenghi, notableWork, Shoeshine]
-
A.
Shoeshine Boy
"Shoeshine Boy" is a 1974 soul and R&B hit single by Eddie Kendricks that showcases his smooth falsetto style and post-Temptations solo success.
-
B.
Shoe-Shine
chosen
Shoe-Shine is a 1946 Italian neorealist drama film directed by Vittorio De Sica, celebrated for its poignant portrayal of impoverished youth in postwar Rome.
-
C.
Dodsworth
Dodsworth is a 1936 drama film, based on Sinclair Lewis's novel, that explores the disintegration of a wealthy American couple's marriage during a European trip.
-
D.
The Salesman
The Salesman is an acclaimed 2016 Iranian drama film directed by Asghar Farhadi that explores moral conflict and social tensions in contemporary Tehran.
-
E.
The Loved One
The Loved One is a darkly comic novella by Evelyn Waugh that satirizes the American funeral industry and Hollywood culture.
- 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_69d806b886bc8190b676e7768b8e01c5 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dba0d74e5881909828854bba7d9a87 |
completed | April 12, 2026, 1:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7306fb8348190a325a07a1ac858fd |
completed | May 3, 2026, 11:24 a.m. |
Created at: April 9, 2026, 9:34 p.m.