Triple
T246517
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter Griffin |
E5049
|
entity |
| Predicate | friend |
P8712
|
FINISHED |
| Object | Joe Swanson |
E27233
|
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: Joe Swanson | Statement: [Peter Griffin, friend, Joe Swanson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joe Swanson Context triple: [Peter Griffin, friend, Joe Swanson]
-
A.
Joe Swanson
chosen
Joe Swanson is a paraplegic, tough but good-hearted police officer and one of Peter Griffin’s closest friends in the animated sitcom "Family Guy."
-
B.
Frank Sullivan
Frank Sullivan is an American college basketball coach best known for his long tenure leading the Harvard Crimson men's basketball program.
-
C.
Mike Henry
Mike Henry is an American actor, comedian, and writer best known for voicing characters such as Cleveland Brown on the animated television series Family Guy and its spin-off The Cleveland Show.
-
D.
John Monk Saunders
John Monk Saunders was an American novelist and Academy Award–winning screenwriter best known for his aviation-themed stories and the film "The Dawn Patrol."
-
E.
Leslie Nielsen
Leslie Nielsen was a Canadian-American actor best known for his deadpan comedic roles in films like Airplane! and The Naked Gun series after an earlier career in dramatic television and film.
- 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_69a257c4bf688190a46ebbf411ab7473 |
completed | Feb. 28, 2026, 2:49 a.m. |
| NER | Named-entity recognition | batch_69a260c592cc8190bc642fcd248a1f1b |
completed | Feb. 28, 2026, 3:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a3837270f88190af91bab054bd1fbb |
completed | March 1, 2026, 12:08 a.m. |
Created at: Feb. 28, 2026, 2:54 a.m.