Triple
T30102742
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Muhammad Ali–Ken Norton boxing trilogy |
E765041
|
entity |
| Predicate | firstFightState |
P102208
|
FINISHED |
| Object | California |
—
|
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: California | Statement: [Muhammad Ali–Ken Norton boxing trilogy, firstFightState, California]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstFightState Context triple: [Muhammad Ali–Ken Norton boxing trilogy, firstFightState, California]
-
A.
firstFight
chosen
Indicates that the referenced event is the initial instance in which the involved entities engaged in a fight or combat with each other.
-
B.
secondFightState
Indicates the condition or status of an entity during its second instance of a fight or combat encounter.
-
C.
thirdFightState
Indicates the condition or status of the entities involved during the third occurrence of a fight or combat interaction.
-
D.
firstBoutResult
Indicates the outcome or result of an entity’s initial bout, match, or contest.
-
E.
firstStruck
Indicates that one entity was the initial party to hit, attack, or make physical contact with another in a conflict or interaction.
- F. None of above.
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_69f22474e4288190b5f895fe3974aa92 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a0191d96dc88190ac0823e534f9d704 |
completed | May 11, 2026, 8:22 a.m. |
| PD | Predicate disambiguation | batch_6a01908110448190a46442ffe4d15f5f |
completed | May 11, 2026, 8:17 a.m. |
Created at: April 29, 2026, 7:08 p.m.