Triple
T810921
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mark Zuckerberg |
E17541
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Priscilla Chan |
E2633
|
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: Priscilla Chan | Statement: [Mark Zuckerberg, spouse, Priscilla Chan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Priscilla Chan Context triple: [Mark Zuckerberg, spouse, Priscilla Chan]
-
A.
Priscilla Chan
chosen
Priscilla Chan is an American pediatrician and philanthropist who co-founded the Chan Zuckerberg Initiative with her husband, Facebook co-founder Mark Zuckerberg.
-
B.
Vivian Chan
Vivian Chan is a personal name shared by multiple individuals, including professionals in fields such as science, media, and business.
-
C.
Anita Chan
Anita Chan is a prominent scholar known for her influential research on Chinese labor issues and labor rights.
-
D.
Eileen Loo
Eileen Loo was the wife of renowned Chinese-American architect I. M. Pei and a supportive partner throughout his celebrated career.
-
E.
Marina Chin
Marina Chin is a former Malaysian national hurdler and prominent sports figure who gained recognition for her achievements in athletics and her role in major national sporting events.
- 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_69a4937ae8a08190b5084a03d532b30e |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4ab282fe48190a05ee97550843cd7 |
completed | March 1, 2026, 9:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a7edfcb7a88190b3670c6ef2b93609 |
completed | March 4, 2026, 8:31 a.m. |
Created at: March 1, 2026, 7:38 p.m.