Triple
T13609085
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cliff Clavin |
E325139
|
entity |
| Predicate | hasFriend |
P8712
|
FINISHED |
| Object | Norm Peterson |
E325138
|
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: Norm Peterson | Statement: [Cliff Clavin, hasFriend, Norm Peterson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Norm Peterson Context triple: [Cliff Clavin, hasFriend, Norm Peterson]
-
A.
Norm Peterson
chosen
Norm Peterson is a lovable, wisecracking bar regular from the sitcom "Cheers," known for his perpetual presence on a barstool and his humorous one-liners.
-
B.
Robert Peterson
Robert Peterson is an individual known primarily as a relative of Zaria Peterson.
-
C.
Robert Peterson
Robert Peterson was the husband of American film and television actress Joan Caulfield.
-
D.
Robert Peterson
Robert Peterson is the central father figure and protagonist of the 1990s American sitcom "The Parent 'Hood," around whom the show's family-centered stories revolve.
-
E.
Don Peters
Don Peters is a character in Stephen King and Owen King's novel "Sleeping Beauties," involved in the unfolding crisis when women worldwide fall into a mysterious sleep.
- 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_69d80769eaf081909d82f44e484d6113 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbb07f462c8190b5b5e115d550037f |
completed | April 12, 2026, 2:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f78ae56e2081909c0fd044ce3730a9 |
completed | May 3, 2026, 5:50 p.m. |
Created at: April 9, 2026, 9:50 p.m.