Triple
T23559117
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sandman Sims |
E579178
|
entity |
| Predicate | birthName |
P65
|
FINISHED |
| Object | Howard Sims |
—
|
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: Howard Sims | Statement: [Sandman Sims, birthName, Howard Sims]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Howard Sims Context triple: [Sandman Sims, birthName, Howard Sims]
-
A.
Howard Sims
chosen
Howard Sims was an influential American tap dancer renowned for his virtuosic rhythm tap style and his long association with New York’s Apollo Theater.
-
B.
Dick Sims
Dick Sims was an American keyboardist best known for his work with Eric Clapton in the 1970s, contributing to several of Clapton’s classic recordings and tours.
-
C.
Ed Sims
Ed Sims is a business executive best known for serving as the president and CEO of WestJet Airlines.
-
D.
Michael Sims
Michael Sims is an American author and essayist known for his works on nature, science, and cultural history.
-
E.
Charles Simmons
Charles Simmons was an American author and editor known for his witty, elegantly crafted novels and his long association with The New York Times Book Review.
- 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_69f1af6663e0819081d654da38cf3aa9 |
completed | April 29, 2026, 7:12 a.m. |
Created at: April 17, 2026, 6:12 p.m.