Triple
T10838164
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tyreek Hill |
E255814
|
entity |
| Predicate | fullName |
P16
|
FINISHED |
| Object | Tyreek Hill |
E255814
|
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: Tyreek Hill | Statement: [Tyreek Hill, fullName, Tyreek Hill]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tyreek Hill Context triple: [Tyreek Hill, fullName, Tyreek Hill]
-
A.
Tyreek Hill
chosen
Tyreek Hill is an NFL wide receiver renowned for his elite speed and big-play ability, currently starring for the Miami Dolphins.
-
B.
Calvin Ridley
Calvin Ridley is an American football wide receiver known for his productive NFL career, highlighted by his early years with the Atlanta Falcons.
-
C.
Jharrel Jerome
Jharrel Jerome is an American actor known for his breakout role in the film "Moonlight" and his Emmy-winning performance in the miniseries "When They See Us."
-
D.
Ja'Marr Chase
Ja'Marr Chase is an NFL wide receiver known for his explosive playmaking and Pro Bowl production with the Cincinnati Bengals after a standout college career at LSU.
-
E.
Damian Harris
Damian Harris is a British film director and screenwriter known for directing psychological thrillers and character-driven dramas, including the 1995 film "Bad Company."
- 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_69d6aa81a5d08190aa86689061d1ddd2 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d747002b3081908726901ee83d8f38 |
completed | April 9, 2026, 6:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69deb139072081908a67e76a83575c32 |
completed | April 14, 2026, 9:27 p.m. |
Created at: April 8, 2026, 9:19 p.m.