Triple
T22945824
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paul Krekorian |
E569862
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Paul Krekorian |
—
|
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: Paul Krekorian | Statement: [Paul Krekorian, name, Paul Krekorian]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul Krekorian Context triple: [Paul Krekorian, name, Paul Krekorian]
-
A.
Paul Krekorian
chosen
Paul Krekorian is an American politician and attorney serving as a member of the Los Angeles City Council and a prominent local Democratic leader.
-
B.
Charles Boustany
Charles Boustany is an American politician and former Republican U.S. Representative from Louisiana.
-
C.
Mark Vahradian
Mark Vahradian is a film producer best known for his work on major action and thriller movies, including the Tom Clancy–based Jack Ryan franchise.
-
D.
Michel E. Mawad
Michel E. Mawad is a Lebanese-American physician and academic leader who serves as president of the Lebanese American University.
-
E.
Michael A. Goorjian
Michael A. Goorjian is an American actor, director, and writer known for roles in films like "SLC Punk!" and the TV series "Party of Five," as well as for his work in independent cinema.
- 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_69e2459199d08190a8184ee2aa935842 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1819d2d7881909e6390717ff79df0 |
completed | April 29, 2026, 3:57 a.m. |
Created at: April 17, 2026, 3:45 p.m.