Triple
T19550049
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paradise (1997 novel) |
E489173
|
entity |
| Predicate | featuresCharacter |
P626
|
FINISHED |
| Object | Gigi |
—
|
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: Gigi | Statement: [Paradise (1997 novel), featuresCharacter, Gigi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gigi Context triple: [Paradise (1997 novel), featuresCharacter, Gigi]
-
A.
Gigi
Gigi is a 1958 American musical romantic comedy film, directed by Vincente Minnelli, that won multiple Academy Awards and is celebrated for its lavish production and memorable score.
-
B.
Gigi
Gigi is a principal bar girl character in the musical *Miss Saigon*, known for her poignant solo "The Movie in My Mind" and her role as a close friend of the heroine Kim.
-
C.
Gigi
Gigi was the affectionate nickname of Gianna Bryant, the late daughter of NBA legend Kobe Bryant who was known for her own promising basketball talent.
-
D.
Gigi
chosen
Gigi is a resident of the Convent, a communal living space central to Toni Morrison’s novel "Paradise."
-
E.
Gigi
Gigi is the affectionate nickname of Gigi Proietti, a renowned Italian actor, comedian, and director celebrated for his work in theater, film, and television.
- 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_69d8e8dc5d8c8190a6d7bd8864f43ca0 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e63d2f39188190976e8b6b111499a0 |
completed | April 20, 2026, 2:50 p.m. |
Created at: April 10, 2026, 1:41 p.m.