Triple
T19009810
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Barry Prendergast |
E465189
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Jane Birkin |
—
|
NE NERFINISHED |
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: Jane Birkin | Statement: [John Barry Prendergast, spouse, Jane Birkin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jane Birkin Context triple: [John Barry Prendergast, spouse, Jane Birkin]
-
A.
Jane Birkin
chosen
Jane Birkin was an English-French actress and singer renowned for her artistic partnership with Serge Gainsbourg and her enduring influence on fashion and popular culture.
-
B.
Sylvie Vartan
Sylvie Vartan is a Bulgarian-born French pop singer and actress who became one of France’s most popular yé-yé idols in the 1960s.
-
C.
Vanessa Paradis
Vanessa Paradis is a French singer, actress, and model who gained fame as a teen pop star and later for her long-term relationship with actor Johnny Depp.
-
D.
Leila Roker
Leila Roker is an American media personality and journalist known as the daughter of longtime television weather anchor and host Al Roker.
-
E.
Françoise Brion
Françoise Brion is a French actress known for her work in European cinema from the 1960s onward, including collaborations with prominent auteurs.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dd025c188190a1d81f5b4ec7e2c6 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d6a8225c81908e80ae7eb1c1301b |
completed | April 20, 2026, 7:32 a.m. |
Created at: April 10, 2026, 12:02 p.m.