Triple
T19645713
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Lang |
E471665
|
entity |
| Predicate | coFoundedWith |
P2835
|
FINISHED |
| Object | Joel Rosenman |
—
|
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: Joel Rosenman | Statement: [Michael Lang, coFoundedWith, Joel Rosenman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joel Rosenman Context triple: [Michael Lang, coFoundedWith, Joel Rosenman]
-
A.
Joel Rosenman
chosen
Joel Rosenman is an American lawyer, entrepreneur, and music producer best known as one of the principal backers and co-creators of the 1969 Woodstock music festival.
-
B.
Joe Masteroff
Joe Masteroff was an American playwright and librettist best known for writing the book for the musical "Cabaret."
-
C.
Robert Kravis
Robert Kravis is a film producer best known for his work on the crime thriller "Lucky Number Slevin."
-
D.
Peter Seligmann
Peter Seligmann is an American environmentalist and business leader best known for co-founding and leading the global conservation organization Conservation International.
-
E.
Paul Kagan
Paul Kagan was an influential American media industry analyst and investment banker known for his pioneering research and deal-making in the cable television and communications sectors.
- 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_69d8e51395348190ac1416d46dfc6db0 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e641250e108190a707452fefc87041 |
completed | April 20, 2026, 3:07 p.m. |
Created at: April 10, 2026, 1:44 p.m.