Triple
T15333873
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yahoo |
E366609
|
entity |
| Predicate | coFounder |
P2835
|
FINISHED |
| Object | David Filo |
E1025693
|
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: David Filo | Statement: [Yahoo, coFounder, David Filo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Filo Context triple: [Yahoo, coFounder, David Filo]
-
A.
David Filo
chosen
David Filo is an American billionaire entrepreneur best known as the co-founder of the web services company Yahoo!.
-
B.
John Filo
John Filo is an American photojournalist best known for his Pulitzer Prize–winning photograph capturing the aftermath of the Kent State shootings in 1970.
-
C.
Jeff Marx
Jeff Marx is an American composer and lyricist best known for co-creating and co-writing the music and lyrics for the Tony Award–winning musical Avenue Q.
-
D.
Nick Mitzevich
Nick Mitzevich is an Australian art curator and museum director known for leading major national art institutions, including the National Gallery of Australia.
-
E.
Steve Pearlman
Steve Pearlman is a television producer best known for his work on various American drama series.
- 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_69d85a121520819093dcce999fdefe1a |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03e0268608190947a58f559a67717 |
completed | April 16, 2026, 1:40 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff0b3f8eac81908489baeb4cb6bb53 |
completed | May 9, 2026, 10:23 a.m. |
Created at: April 10, 2026, 3:17 a.m.