Triple
T6389297
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Regnery Publishing |
E143777
|
entity |
| Predicate | hasPublished |
P80
|
FINISHED |
| Object | Mark Levin |
E565008
|
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: Mark Levin | Statement: [Regnery Publishing, hasPublished, Mark Levin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Levin Context triple: [Regnery Publishing, hasPublished, Mark Levin]
-
A.
Mark Levin
chosen
Mark Levin is a conservative American lawyer, author, and talk radio and television host known for his outspoken commentary on U.S. politics and constitutional issues.
-
B.
John Batchelor
John Batchelor is an Australian actor known for his work in film, television, and theatre.
-
C.
Pete Nance
Pete Nance is an American professional basketball player known for his collegiate career at Northwestern and North Carolina and as the son of former NBA All-Star Larry Nance.
-
D.
Sean Hannity
Sean Hannity is a conservative American television and radio host best known for his long-running prime-time show on Fox News.
-
E.
Bill O’Reilly
Bill O’Reilly is an American conservative political commentator, author, and former long-time host of the Fox News program "The O’Reilly Factor."
- 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_69c008db906c819096f3597d55d95432 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c0686cc6d481909c62a29a84a4ce8e |
completed | March 22, 2026, 10:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c640b7e89881908e1c39d45e8a8473 |
completed | March 27, 2026, 8:32 a.m. |
Created at: March 22, 2026, 4:34 p.m.