Triple
T13088480
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Revson Fountain |
E310397
|
entity |
| Predicate | namedAfter |
P63
|
FINISHED |
| Object | Charles H. Revson |
E264935
|
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: Charles H. Revson | Statement: [Revson Fountain, namedAfter, Charles H. Revson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Charles H. Revson Context triple: [Revson Fountain, namedAfter, Charles H. Revson]
-
A.
Charles Revson
chosen
Charles Revson was an American businessman and cosmetics industry pioneer best known as the founder and longtime head of Revlon.
-
B.
Herman Bergdorf
Herman Bergdorf was a German-born American tailor and businessman best known as the co-founder of the luxury department store Bergdorf Goodman in New York City.
-
C.
Joseph Revson
Joseph Revson was an American businessman best known as a co-founder of the major cosmetics company Revlon.
-
D.
Leonard I. Schiff
Leonard I. Schiff was an American theoretical physicist known for his work in quantum mechanics and for authoring the influential textbook "Quantum Mechanics."
-
E.
Sidney Taylor
Sidney Taylor is a banking executive who served in a supervisory leadership role at Meritor Savings Bank, FSB.
- 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_69d806a733548190989cfd4ce981ca33 |
completed | April 9, 2026, 8:05 p.m. |
| NER | Named-entity recognition | batch_69d98138a1d481908a139f2f67eb3472 |
completed | April 10, 2026, 11:01 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6d614704481908758cf8691a941ea |
completed | May 3, 2026, 4:59 a.m. |
Created at: April 9, 2026, 9:02 p.m.