Triple
T19612540
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Phillips |
E470768
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Geneviève Waïte |
—
|
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: Geneviève Waïte | Statement: [John Phillips, spouse, Geneviève Waïte]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Geneviève Waïte Context triple: [John Phillips, spouse, Geneviève Waïte]
-
A.
Geneviève Waïte
chosen
Geneviève Waïte was a South African-born actress, singer, and model known for her work in the 1960s and 1970s and her marriage to musician John Phillips.
-
B.
Genevieve Morris
Genevieve Morris is an Australian actress and comedian known for her work in television sketch comedy and character roles.
-
C.
Genevieve Hughes
Genevieve Hughes is known primarily as the sister of American Olympic figure skating champion Sarah Hughes.
-
D.
Geneviève Emery
Geneviève Emery is the young, romantic heroine of Jacques Demy's musical film "The Umbrellas of Cherbourg," whose love story with Guy Foucher unfolds entirely through song.
-
E.
Margaret Ménégoz
Margaret Ménégoz is a French film producer known for her work on acclaimed European art-house films, including Wim Wenders' "Paris, Texas."
- 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_69d8e510fa248190b7afb274a1d4cf73 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e640cbeda08190addb1adf84af4993 |
completed | April 20, 2026, 3:05 p.m. |
Created at: April 10, 2026, 1:43 p.m.