Triple
T18888398
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Big Man on Campus |
E462017
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Jeremy Kagan |
—
|
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: Jeremy Kagan | Statement: [Big Man on Campus, director, Jeremy Kagan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jeremy Kagan Context triple: [Big Man on Campus, director, Jeremy Kagan]
-
A.
Jeremy Kagan
chosen
Jeremy Kagan is an American film and television director, producer, and screenwriter known for his work on character-driven dramas and socially conscious projects.
-
B.
Neil Kagan
Neil Kagan is an American editor and author known for producing richly illustrated historical and reference books, particularly for National Geographic.
-
C.
Jason Kliot
Jason Kliot is an American film producer known for his work on independent and documentary films, including the acclaimed Enron exposé "Enron: The Smartest Guys in the Room."
-
D.
Jared Kaplan
Jared Kaplan is a theoretical physicist and AI researcher known for his work on deep learning scaling laws and contributions to large language model development.
-
E.
Jeremy Stoppelman
Jeremy Stoppelman is an American entrepreneur best known as the co-founder and longtime CEO of Yelp, a popular online review platform for local businesses.
- 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_69d8dcfc3430819095ee6fc0eb4c06a5 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c478d8c481909291e7c471e5095a |
completed | April 20, 2026, 6:15 a.m. |
Created at: April 10, 2026, 11:58 a.m.