Triple
T2141901
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leslie Caron |
E46776
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Gigi |
E136797
|
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: Gigi | Statement: [Leslie Caron, notableWork, Gigi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gigi Context triple: [Leslie Caron, notableWork, Gigi]
-
A.
Gigi
chosen
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 was the affectionate nickname of Gianna Bryant, the late daughter of NBA legend Kobe Bryant who was known for her own promising basketball talent.
-
C.
Annette
Annette is a feminine given name of French origin, commonly used in various European and English-speaking countries.
-
D.
Coco
Coco is a 2017 Pixar animated film that follows a young Mexican boy’s journey through the Land of the Dead as he uncovers his family’s history and celebrates Día de los Muertos.
-
E.
Elle
Elle is a globally recognized fashion and lifestyle magazine known for its coverage of style, beauty, culture, and celebrity features.
- 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_69a88a174ab48190a5db20c132e5dccf |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abbe0543108190862dd9a4a861c758 |
completed | March 7, 2026, 5:56 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae51b63e4081908a5d87af5d17d3c4 |
completed | March 9, 2026, 4:51 a.m. |
Created at: March 4, 2026, 7:44 p.m.