Triple
T23559530
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Susan Birkenhead |
E579194
|
entity |
| Predicate | collaboratedWith |
P435
|
FINISHED |
| Object | Cy Coleman |
—
|
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: Cy Coleman | Statement: [Susan Birkenhead, collaboratedWith, Cy Coleman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cy Coleman Context triple: [Susan Birkenhead, collaboratedWith, Cy Coleman]
-
A.
Cy Coleman
chosen
Cy Coleman was an American composer and songwriter best known for his work on Broadway musicals such as "Sweet Charity," "Barnum," and "City of Angels."
-
B.
SY Coleman
SY Coleman is a company that employed American actor and director Jay Garner.
-
C.
Kevin Coleman
Kevin Coleman is a musician best known as a member of the American rock band Smash Mouth.
-
D.
Kevin Coleman
Kevin Coleman is an American local politician serving as the mayor of Westland, Michigan.
-
E.
Neil Cole
Neil Cole is a British television presenter and comedian known for his work on various UK and international entertainment and music shows.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245fe24588190888f3aec8407d8e3 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f1af672db4819087dbff2c0dfadd7f |
completed | April 29, 2026, 7:12 a.m. |
Created at: April 17, 2026, 6:12 p.m.