Triple
T9885115
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Licence to Kill |
E180910
|
entity |
| Predicate | featuresCharacter |
P626
|
FINISHED |
| Object | Pam Bouvier |
E679257
|
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: Pam Bouvier | Statement: [Licence to Kill, featuresCharacter, Pam Bouvier]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pam Bouvier Context triple: [Licence to Kill, featuresCharacter, Pam Bouvier]
-
A.
Pam Bouvier
chosen
Pam Bouvier is a resourceful and tough CIA informant and Bond girl who assists James Bond in his mission in the 1989 film "Licence to Kill."
-
B.
Deanna Dwyer
Deanna Dwyer is a pseudonym used by bestselling American suspense and horror author Dean Koontz early in his writing career.
-
C.
Patty Larkin
Patty Larkin is an American singer-songwriter and innovative contemporary folk guitarist known for her poetic lyrics and intricate acoustic work.
-
D.
Pam Brady
Pam Brady is an American television and film writer and producer best known for her work on "South Park" and various comedy projects.
-
E.
Amy Ferson
Amy Ferson is an American journalist and commentator best known as the first wife of television personality and news anchor T. J. Holmes.
- 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_69ca828082cc8190a40f8d299caa6545 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cdb45549488190833200977d558e47 |
completed | April 2, 2026, 12:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d22891cb4c8190b4d378749599bdda |
completed | April 5, 2026, 9:17 a.m. |
Created at: March 30, 2026, 8:38 p.m.