Triple
T33552792
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Simon Pegg as Gary King |
E859383
|
entity |
| Predicate | friendCharacter |
P78618
|
FINISHED |
| Object | Andy Knightley |
—
|
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: Andy Knightley | Statement: [Simon Pegg as Gary King, friendCharacter, Andy Knightley]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: friendCharacter Context triple: [Simon Pegg as Gary King, friendCharacter, Andy Knightley]
-
A.
relatedCharacter
Indicates that one character has a specified relationship or association with another character.
-
B.
featuresCharacterWith
Indicates that one entity (such as a work or product) includes or presents a particular character as part of its content.
-
C.
isFriendOfProtagonist
chosen
Indicates that one entity is a friend or close ally of the story’s main character.
-
D.
exampleCharacter
Indicates that one entity is an illustrative or sample character associated with another entity, typically used for demonstration or example purposes.
-
E.
metCharacter
Indicates that one entity has encountered or been introduced to another entity at least once.
- F. None of above.
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_69f3497b2b68819093207971b5e13dc8 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6f70c17d88190aa74afc2dd2a0467 |
completed | May 3, 2026, 7:19 a.m. |
| PD | Predicate disambiguation | batch_69f6f6632dfc8190af85e258c8519207 |
completed | May 3, 2026, 7:16 a.m. |
Created at: May 1, 2026, 1:40 a.m.