Triple
T21038226
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jersey Joe Walcott |
E518248
|
entity |
| Predicate | fought |
P30824
|
FINISHED |
| Object | Joey Maxim |
—
|
NE NERFINISHED |
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: Joey Maxim | Statement: [Jersey Joe Walcott, fought, Joey Maxim]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joey Maxim Context triple: [Jersey Joe Walcott, fought, Joey Maxim]
-
A.
Joey Maxim
chosen
Joey Maxim was an American professional boxer and world light heavyweight champion known for his technical skill and durability in the ring.
-
B.
Joey Curtis
Joey Curtis is a filmmaker and screenwriter known for his work in independent cinema and visually driven storytelling.
-
C.
Joey Curtis
Joey Curtis is a screenwriter best known for co-writing the critically acclaimed romantic drama film "Blue Valentine."
-
D.
Joey Williams
Joey Williams is an American gospel musician and guitarist best known for his work with the legendary vocal group The Blind Boys of Alabama.
-
E.
Joey Zimmerman
Joey Zimmerman is an American actor best known for playing Dylan Piper in Disney Channel’s "Halloweentown" film series.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b50438e08190917e2538bb8bc034 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fcee13b08190a8b3372f6759cd1b |
completed | April 21, 2026, 4:28 a.m. |
Created at: April 16, 2026, 2:05 p.m.