Triple
T12686143
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Polisse |
E303071
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Lou Doillon |
E434241
|
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: Lou Doillon | Statement: [Polisse, starring, Lou Doillon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lou Doillon Context triple: [Polisse, starring, Lou Doillon]
-
A.
Lou Doillon
chosen
Lou Doillon is a French singer-songwriter, actress, and model known for her distinctive husky voice and work in both music and film.
-
B.
Eve Hewson
Eve Hewson is an Irish actress known for her roles in films like "The Knick," "Bridge of Spies," and the series "Bad Sisters."
-
C.
Frances O'Connor
Frances O'Connor is an English-Australian actress known for her work in film and television, including prominent roles in dramas and period pieces.
-
D.
Sinéad Cusack
Sinéad Cusack is an acclaimed Irish stage and screen actress known for her work with the Royal Shakespeare Company and in numerous film and television roles.
-
E.
Lois O’Connor
Lois O’Connor was the wife of acclaimed American stage and film actor Jason Robards.
- 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_69d7bdee64a08190801c6d470aefd723 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d961d7cd4c81909521839ef5859799 |
completed | April 10, 2026, 8:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f671a8f068819086e2191439607f76 |
completed | May 2, 2026, 9:50 p.m. |
Created at: April 9, 2026, 5:21 p.m.