Triple
T17823518
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Burt Lancaster |
E445050
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Susan Martin |
—
|
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: Susan Martin | Statement: [Burt Lancaster, spouse, Susan Martin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Susan Martin Context triple: [Burt Lancaster, spouse, Susan Martin]
-
A.
Susan Martin
chosen
Susan Martin is best known as the longtime wife of acclaimed American actor Burt Lancaster.
-
B.
Donna Martin
Donna Martin is a central character on the teen drama series "Beverly Hills, 90210," known for her sweet personality, evolving fashion sense, and storylines about relationships and personal growth.
-
C.
Patricia Denner Cayne
Patricia Denner Cayne is best known as the wife of James Cayne, the former CEO and chairman of Bear Stearns.
-
D.
Susan Mara
Susan Mara is a member of the Mara family, the longtime owners of the NFL’s New York Giants franchise.
-
E.
Colleen Sharp
Colleen Sharp is a film editor best known for her work on Terrence Malick’s acclaimed drama "Days of Heaven."
- 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_69d8b9f0de78819099395b14db75a8a6 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4891282a081908d384d45bf444baf |
completed | April 19, 2026, 7:49 a.m. |
Created at: April 10, 2026, 10:15 a.m.