Triple
T13384430
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Neon Demon |
E319402
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Abbey Lee |
E195750
|
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: Abbey Lee | Statement: [The Neon Demon, starring, Abbey Lee]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Abbey Lee Context triple: [The Neon Demon, starring, Abbey Lee]
-
A.
Abbey Lee
chosen
Abbey Lee is an Australian model and actress best known for her role as one of the wives in the post-apocalyptic action film "Mad Max: Fury Road."
-
B.
Gaby Lee
Gaby Lee is an early stage name used by the acclaimed American jazz vocalist, songwriter, and civil rights activist Abbey Lincoln.
-
C.
Leah Lee
Leah Lee was the wife of French Symbolist poet Jules Laforgue, known primarily through her association with his brief, influential life and work.
-
D.
Abby Park
Abby Park is an energetic, passionate, and fiercely loyal friend in Pixar's animated film "Turning Red," known for her bold personality and love of boy bands.
-
E.
Joie Lee
Joie Lee is an American actress, screenwriter, and producer best known for her frequent collaborations with her brother Spike Lee in films exploring African-American life and 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_69dadce80158819082156eaeaeda3bd8 |
completed | April 11, 2026, 11:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7268cf04c8190a35fd48ce81c149e |
completed | May 3, 2026, 10:42 a.m. |
Created at: April 9, 2026, 9:33 p.m.