Triple
T510785
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ron Perlman |
E10602
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Perlman |
E34027
|
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: Perlman | Statement: [Ron Perlman, familyName, Perlman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Perlman Context triple: [Ron Perlman, familyName, Perlman]
-
A.
Itzhak Perlman
chosen
Itzhak Perlman is an acclaimed Israeli-American violinist renowned for his virtuosity, rich tone, and interpretations of the classical repertoire.
-
B.
Edgar Meyer
Edgar Meyer is an acclaimed American double bassist and composer known for his genre-crossing work in classical, bluegrass, and contemporary music.
-
C.
Alan Shorter
Alan Shorter was an American jazz trumpeter and flugelhornist known for his avant-garde and experimental contributions to the 1960s jazz scene.
-
D.
Ludwik Rajchman
Ludwik Rajchman was a Polish physician and epidemiologist best known as a leading public health expert for the League of Nations and as a founder of UNICEF.
-
E.
Janno Lieber
Janno Lieber is an American public official and transportation executive who leads New York’s Metropolitan Transportation Authority, overseeing the city’s vast subway, bus, and commuter rail systems.
- 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_69a2e84a0d08819087e01863fcd9abf1 |
completed | Feb. 28, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69a2f165b91c81908c2d2ba15c64b956 |
completed | Feb. 28, 2026, 1:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a49ebcf4408190bbbff6e86f42034f |
completed | March 1, 2026, 8:17 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.