Triple
T4145967
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Phil Bryant |
E89382
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Bryant |
E213940
|
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: Bryant | Statement: [Phil Bryant, familyName, Bryant]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bryant Context triple: [Phil Bryant, familyName, Bryant]
-
A.
Bryant
Bryant is the middle name of James B. Conant, the influential American chemist, educator, and president of Harvard University.
-
B.
Bryant
chosen
Bryant is a common English surname borne by numerous notable figures in American history, literature, sports, and public life.
-
C.
Kobe Bryant
Kobe Bryant was an American professional basketball player, primarily with the Los Angeles Lakers, widely regarded as one of the greatest players in NBA history.
-
D.
Earvin
Earvin is the given first name of Magic Johnson, the legendary American basketball player and NBA Hall of Famer.
-
E.
Maye
Maye is the first name of Maye Musk, a Canadian-South African model and dietitian known for her long-running fashion career and as the mother of entrepreneur Elon Musk.
- 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_69aed95785788190ae75bcf0cd1cafdf |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af025fef088190b42515d0a854a1ae |
completed | March 9, 2026, 5:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b576d5379081908300afbb3a6fe5e4 |
completed | March 14, 2026, 2:55 p.m. |
Created at: March 9, 2026, 3:43 p.m.