Triple
T19887410
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jean Kent |
E477936
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Joseph Janni |
E1023733
|
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: Joseph Janni | Statement: [Jean Kent, spouse, Joseph Janni]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joseph Janni Context triple: [Jean Kent, spouse, Joseph Janni]
-
A.
Joseph Janni
chosen
Joseph Janni was an Italian-born British film producer known for his influential work in mid-20th-century British cinema, including collaborations with director John Schlesinger.
-
B.
Robert Glaudini
Robert Glaudini is an American playwright, screenwriter, and actor best known for writing the play "Jack Goes Boating," which he later adapted for the film version.
-
C.
Louis Cioffi
Louis Cioffi is a film editor known for his work on feature films, including the crime drama "Wonderland" (2003).
-
D.
Victor Raimondi
Victor Raimondi is the central male protagonist in the film "The Girl Who Had Everything," serving as the romantic interest whose involvement complicates the life of the seemingly privileged heroine.
-
E.
John Bagni
John Bagni was an American actor and screenwriter active in mid-20th-century film and radio.
- 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_69d8e51f32b08190b3687f4f60353250 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6590b12c08190bf44a3f3b2cb9122 |
completed | April 20, 2026, 4:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a07dbd16ff08190b03caa3b20478ef4 |
completed | May 16, 2026, 2:52 a.m. |
Created at: April 10, 2026, 1:52 p.m.