Triple
T30102750
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Muhammad Ali–Ken Norton boxing trilogy |
E765041
|
entity |
| Predicate | secondFightOutcome |
P165809
|
FINISHED |
| Object | Muhammad Ali defeated Ken Norton by split decision |
—
|
LITERAL 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: Muhammad Ali defeated Ken Norton by split decision | Statement: [Muhammad Ali–Ken Norton boxing trilogy, secondFightOutcome, Muhammad Ali defeated Ken Norton by split decision]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: secondFightOutcome Context triple: [Muhammad Ali–Ken Norton boxing trilogy, secondFightOutcome, Muhammad Ali defeated Ken Norton by split decision]
-
A.
secondFight
Indicates that an entity engages in a second instance of a fight or combat interaction with another entity.
-
B.
secondFightState
Indicates the condition or status of an entity during its second instance of a fight or combat encounter.
-
C.
secondFightLocation
Indicates the location where the second fight or confrontation between the involved entities takes place.
-
D.
secondFightCity
Indicates that an entity engaged in its second fight or battle in the specified city.
-
E.
secondBoutResult
chosen
Indicates the outcome or result of the second bout in a sequence of contests or matches.
- 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_69fd974d75e08190af46b1d608769f3b |
completed | May 8, 2026, 7:57 a.m. |
| PD | Predicate disambiguation | batch_69fd94ff792c8190bedf4a639d3da809 |
completed | May 8, 2026, 7:47 a.m. |
Created at: April 29, 2026, 7:08 p.m.