Triple
T864507
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | James Bond |
E18670
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Tracy Bond |
E194260
|
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: Tracy Bond | Statement: [James Bond, spouse, Tracy Bond]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tracy Bond Context triple: [James Bond, spouse, Tracy Bond]
-
A.
Tracy Bond
chosen
Tracy Bond is a fictional character in the James Bond series, best known as the woman James Bond marries in the novel and film "On Her Majesty's Secret Service."
-
B.
Tracy Stevens
Tracy Stevens is best known as the wife of American basketball coach and executive Brad Stevens.
-
C.
Tracy Wolfson
Tracy Wolfson is an American sportscaster best known as a longtime CBS Sports sideline reporter for NFL and college basketball coverage.
-
D.
Tracey Scott Wilson
Tracey Scott Wilson is an American playwright, television writer, and screenwriter known for her work in theater and on series such as "The Americans" and "Fosse/Verdon."
-
E.
Melinda Rogers
Melinda Rogers is a Canadian business executive and member of the Rogers family, known for her leadership roles within Rogers Communications.
- 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_69a4938ce8688190a24bdfef82ba7d21 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4ac6acc148190bcc00a1e939ace77 |
completed | March 1, 2026, 9:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ada0b24844819090904b831c73495c |
completed | March 8, 2026, 4:15 p.m. |
Created at: March 1, 2026, 7:39 p.m.