Triple
T7171208
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Maxwell Gates |
E167198
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Bill Gates |
E20772
|
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: Bill Gates | Statement: [Mary Maxwell Gates, child, Bill Gates]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bill Gates Context triple: [Mary Maxwell Gates, child, Bill Gates]
-
A.
Bill Gates
chosen
Bill Gates is an American business magnate, software pioneer, and philanthropist who co-created the Windows operating system and later co-founded one of the world’s largest charitable foundations.
-
B.
Willard Gates
Willard Gates is a scheming, morally corrupt businessman and secondary antagonist in the 1942 film noir "This Gun for Hire."
-
C.
Steve Ballmer
Steve Ballmer is an American businessman and former Microsoft CEO known for his energetic leadership style and ownership of the NBA’s Los Angeles Clippers.
-
D.
Paul Allen
Paul Allen was an American entrepreneur, investor, and philanthropist best known as the co-founder of Microsoft alongside Bill Gates.
-
E.
Mike Lynch
Mike Lynch is a collegiate athletics administrator best known for leading the athletic department at Babson College.
- 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_69c68889a2748190a316c5e65360361a |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e85ec718819085af59fadee9d22d |
completed | March 27, 2026, 8:28 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7bf8766508190945a96f9536135ef |
completed | March 28, 2026, 11:46 a.m. |
Created at: March 27, 2026, 2:48 p.m.