Triple
T843064
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dustin Moskovitz |
E18217
|
entity |
| Predicate | partnerInBusiness |
P282
|
FINISHED |
| Object | Eduardo Saverin |
E17495
|
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: Eduardo Saverin | Statement: [Dustin Moskovitz, partnerInBusiness, Eduardo Saverin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eduardo Saverin Context triple: [Dustin Moskovitz, partnerInBusiness, Eduardo Saverin]
-
A.
Eduardo Saverin
chosen
Eduardo Saverin is a Brazilian-born entrepreneur and investor best known as one of the original co-founders of Facebook.
-
B.
August Chan Zuckerberg
August Chan Zuckerberg is one of the daughters of Facebook co-founder Mark Zuckerberg and philanthropist Priscilla Chan.
-
C.
Dustin Moskovitz
Dustin Moskovitz is an American entrepreneur and philanthropist best known as a co-founder of Facebook and the productivity software company Asana.
-
D.
Mark Zuckerberg
Mark Zuckerberg is an American technology entrepreneur and philanthropist best known as the co-founder and CEO of Facebook (now Meta Platforms).
-
E.
Reid Hoffman
Reid Hoffman is an American entrepreneur, venture capitalist, and co-founder of LinkedIn, known for his influential role in the tech industry and philanthropy.
- 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_69a4938b04208190b82e1df6b572c548 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4b2b66c908190a52f731119b77a1e |
completed | March 1, 2026, 9:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac257c87b081909f153c8f275c3d45 |
completed | March 7, 2026, 1:17 p.m. |
Created at: March 1, 2026, 7:38 p.m.