Triple
T10458709
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jerami Grant |
E246612
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Jaelin Grant |
E865820
|
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: Jaelin Grant | Statement: [Jerami Grant, sibling, Jaelin Grant]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jaelin Grant Context triple: [Jerami Grant, sibling, Jaelin Grant]
-
A.
Jaelin Grant
chosen
Jaelin Grant is a member of the Grant family, known primarily as a relative of former NBA player Harvey Grant.
-
B.
Angel Reese
Angel Reese is an American college basketball star known for her dominant play, outspoken personality, and leadership in guiding LSU to a national championship.
-
C.
Victoria Oladipo
Victoria Oladipo is known as the sister of NBA player Victor Oladipo.
-
D.
Napheesa Collier
Napheesa Collier is an American professional basketball player and WNBA All-Star known for her standout collegiate career at UConn and her versatile two-way play.
-
E.
Jessica Whiteside
Jessica Whiteside is a geologist and paleoclimatologist known for her research on ancient climate change and mass extinctions.
- 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_69d381c04fe08190957c26c526a3b05a |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4fe4b6d408190af59104a44871578 |
completed | April 7, 2026, 12:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d8dc4fbc3481909b214137f26e243b |
completed | April 10, 2026, 11:17 a.m. |
Created at: April 6, 2026, 12:18 p.m.