Triple
T15863020
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lois Maxwell |
E384637
|
entity |
| Predicate | coStarredWith |
P14987
|
FINISHED |
| Object | George Lazenby |
E103373
|
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: George Lazenby | Statement: [Lois Maxwell, coStarredWith, George Lazenby]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: George Lazenby Context triple: [Lois Maxwell, coStarredWith, George Lazenby]
-
A.
George Lazenby
chosen
George Lazenby is an Australian actor best known for playing James Bond in the 1969 film "On Her Majesty's Secret Service."
-
B.
Jethro Lazenby
Jethro Lazenby was an Australian model, actor, and photographer best known as the son of musician Nick Cave.
-
C.
Roger Moore
Roger Moore was an English actor best known for playing James Bond in seven films from 1973 to 1985.
-
D.
Lazenby
Lazenby is a small village in North Yorkshire, England, situated within the borough of Redcar and Cleveland.
-
E.
Sid James
Sid James was a South African-born British comic actor best known for his roles in the "Carry On" film series and his collaborations with comedian Tony Hancock.
- 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_69d86da422088190aac39e32e6c68429 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1555d38fc8190bd8820bb5b238b71 |
completed | April 16, 2026, 9:32 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffa9439db481908be2f6d8a3cfbc85 |
completed | May 9, 2026, 9:38 p.m. |
Created at: April 10, 2026, 4:50 a.m.