Triple
T21289365
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Susan Hayward |
E524744
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Jess Barker |
—
|
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: Jess Barker | Statement: [Susan Hayward, spouse, Jess Barker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jess Barker Context triple: [Susan Hayward, spouse, Jess Barker]
-
A.
Jess Barker
chosen
Jess Barker was an American film and television actor active in the mid-20th century, known for his roles in crime dramas and noir films.
-
B.
Jeremy Black
Jeremy Black is a British historian renowned for his prolific scholarship on military history, international relations, and the history of warfare.
-
C.
Kim Barker
Kim Barker is an American screenwriter best known for writing the romantic comedy film "License to Wed."
-
D.
Paul Briggs
Paul Briggs is an American animator, storyboard artist, and voice actor best known for his work on Disney animated films such as Frozen and Big Hero 6.
-
E.
Graham Carr
Graham Carr is a Canadian academic and administrator who serves as the president of Concordia University in Montreal.
- 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_69e0b5171f6c8190a5d57201ede73811 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e736d882408190a2300327cb73b7f6 |
completed | April 21, 2026, 8:35 a.m. |
Created at: April 16, 2026, 4:03 p.m.