Triple
T2815708
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Why I Love Baseball |
E54279
|
entity |
| Predicate | mainSubject |
P3
|
FINISHED |
| Object | Larry King |
E194734
|
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: Larry King | Statement: [Why I Love Baseball, mainSubject, Larry King]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Larry King Context triple: [Why I Love Baseball, mainSubject, Larry King]
-
A.
Larry King
chosen
Larry King is an American attorney and promoter best known as the former husband and early manager of tennis legend Billie Jean King.
-
B.
Larry King
Larry King was a legendary American television and radio host best known for his long-running CNN interview show "Larry King Live," where he spoke with world leaders, celebrities, and newsmakers.
-
C.
Mike Wallace
Mike Wallace was a prominent American broadcast journalist best known as a hard-hitting correspondent on the television news magazine "60 Minutes."
-
D.
Matt Lauer
Matt Lauer is an American television journalist and former longtime co-host of NBC's "Today" show.
-
E.
David Brinkley
David Brinkley was a prominent American television newscaster and journalist best known for co-anchoring "The Huntley–Brinkley Report" and later serving as a leading figure in network evening news.
- 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_69ab49de0af08190b3da69683be1e728 |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abde4ed4ac81909f1ec4a3f7869bc1 |
completed | March 7, 2026, 8:14 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b261cda3ac8190b8770e554a66f560 |
completed | March 12, 2026, 6:48 a.m. |
Created at: March 6, 2026, 9:59 p.m.