Triple
T10602594
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Soar |
E275787
|
entity |
| Predicate | developer |
P73
|
FINISHED |
| Object | Paul S. Rosenbloom |
E947730
|
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: Paul S. Rosenbloom | Statement: [Soar, developer, Paul S. Rosenbloom]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul S. Rosenbloom Context triple: [Soar, developer, Paul S. Rosenbloom]
-
A.
Paul S. Rosenbloom
chosen
Paul S. Rosenbloom is a computer scientist and cognitive scientist known for his foundational work in cognitive architectures and artificial intelligence.
-
B.
Daniel G. Bobrow
Daniel G. Bobrow was an influential American computer scientist and early artificial intelligence researcher known for his work on natural language understanding and AI programming systems.
-
C.
Louis J. Horvitz
Louis J. Horvitz is an American television director best known for directing numerous major live awards shows, including multiple Academy Awards broadcasts.
-
D.
Paul F. Edwards
Paul F. Edwards is a television and film screenwriter best known for his work on the acclaimed American Civil War miniseries "North and South."
-
E.
Larry Pizer
Larry Pizer was a British cinematographer known for his work on films such as the cult rock musical "Phantom of the Paradise."
- 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_69d6aaf948d88190806cc3a8c47a3fb2 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d6ded61d5c8190b13890c964b59949 |
completed | April 8, 2026, 11:03 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f2802d74f081909c7af34bf266ae01 |
completed | April 29, 2026, 10:03 p.m. |
Created at: April 8, 2026, 7:31 p.m.