Triple
T4752901
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vanessa Paradis |
E105518
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Lily-Rose Depp |
E102780
|
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-Rose Depp | Statement: [Vanessa Paradis, child, Lily-Rose Depp]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lily-Rose Depp Context triple: [Vanessa Paradis, child, Lily-Rose Depp]
-
A.
Lily-Rose Depp
chosen
Lily-Rose Depp is a French-American actress and model known for roles in films like "The King" and "Voyagers" and for being a prominent figure in contemporary fashion.
-
B.
Lily Aldridge
Lily Aldridge is an American fashion model best known for her work as a Victoria’s Secret Angel and appearances in major magazines such as the Sports Illustrated Swimsuit Issue.
-
C.
Lily Rose Beatrice Allen
Lily Rose Beatrice Allen is an English singer, songwriter, and actress known for her sharp, witty pop songs and outspoken public persona.
-
D.
Lily Mo Sheen
Lily Mo Sheen is a British-American actress and the daughter of actors Michael Sheen and Kate Beckinsale.
-
E.
Suki Waterhouse
Suki Waterhouse is an English model, actress, and singer known for her fashion work, film roles, and music career.
- 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_69bd43f07fa48190954317d01600994a |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd64e5fba88190b1f28d1b0eed3f8e |
completed | March 20, 2026, 3:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be3a5ddf088190892d31275adb39ba |
completed | March 21, 2026, 6:27 a.m. |
Created at: March 20, 2026, 1:20 p.m.