Triple
T1105460
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mila Kunis |
E25478
|
entity |
| Predicate | role |
P268
|
FINISHED |
| Object | Lily in Black Swan |
E52031
|
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: Lily in Black Swan | Statement: [Mila Kunis, role, Lily in Black Swan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lily in Black Swan Context triple: [Mila Kunis, role, Lily in Black Swan]
-
A.
Lily
chosen
Lily is a feminine given name of English origin commonly associated with the lily flower and symbolizing purity and beauty.
-
B.
Lily Bell
Lily Bell is a central character in the television series "Hell on Wheels," portrayed as a determined and resourceful Englishwoman navigating the dangers and politics surrounding the construction of the transcontinental railroad.
-
C.
Lily Idle
Lily Idle is the daughter of British comedian, actor, and Monty Python member Eric Idle.
-
D.
Liza
Liza is a feminine given name most famously associated with American actress and singer Liza Minnelli.
-
E.
Katjana Ballantyne
Katjana Ballantyne is an American politician who serves as the mayor of Somerville, Massachusetts.
- 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_69a49428d4448190b3b36991ceae87ce |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4b9e21f048190bf4b63dd2c7c7641 |
completed | March 1, 2026, 10:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac4c4a402081908ee138257425a336 |
completed | March 7, 2026, 4:03 p.m. |
Created at: March 1, 2026, 7:43 p.m.