Triple
T11686146
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ian Bader |
E277746
|
entity |
| Predicate | associatedWith |
P37
|
FINISHED |
| Object | Henry N. Cobb |
E211114
|
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: Henry N. Cobb | Statement: [Ian Bader, associatedWith, Henry N. Cobb]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Henry N. Cobb Context triple: [Ian Bader, associatedWith, Henry N. Cobb]
-
A.
Henry N. Cobb
chosen
Henry N. Cobb was a prominent American architect and longtime partner at Pei Cobb Freed & Partners, known for designing significant modernist buildings across the United States.
-
B.
Frank B. Wynn
Frank B. Wynn was an American physician, conservationist, and mountaineer known for his pioneering climbs and advocacy for national parks.
-
C.
Charles B. Mulvehill
Charles B. Mulvehill was a film producer best known for his work on the cult classic dark comedy "Harold and Maude."
-
D.
George J. Folsey
George J. Folsey was an American cinematographer renowned for his lush, expressive visual style in classic Hollywood films of the mid-20th century.
-
E.
James A. Contner
James A. Contner is an American cinematographer and television director known for his work on films and numerous TV series.
- 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_69d6aafe02d881909900d54ad7d4af84 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a4654be881909bd0256cf18e25de |
completed | April 10, 2026, 7:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f739644ed48190896d7b2b6c3b5f8f |
completed | May 3, 2026, 12:02 p.m. |
Created at: April 8, 2026, 9:40 p.m.