Triple
T25618064
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roberto Durán in the 1980 "No Más" rematch |
E642210
|
entity |
| Predicate | nicknameOfBoxer |
P159779
|
FINISHED |
| Object | Manos de Piedra |
—
|
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: Manos de Piedra | Statement: [Roberto Durán in the 1980 "No Más" rematch, nicknameOfBoxer, Manos de Piedra]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nicknameOfBoxer Context triple: [Roberto Durán in the 1980 "No Más" rematch, nicknameOfBoxer, Manos de Piedra]
-
A.
winningBoxer
Indicates that one boxer has defeated another in a boxing match and is recognized as the winner.
-
B.
formerBoxer
Indicates that a person previously worked or competed as a boxer but no longer does so.
-
C.
hasNotableBoxer
Indicates that an entity is associated with or characterized by a boxer who is considered notable or distinguished.
-
D.
MuhammadAliPreFightName
Indicates that the given name is the name Muhammad Ali used before he adopted the name "Muhammad Ali" (i.e., his pre-fight or earlier personal name).
-
E.
wasOlympicBoxerFor
Indicates that a person competed as a boxer representing a particular country or team in the Olympic Games.
- F. None of above. chosen
Provenance (4 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_69e77e7a96748190b10f2699041e4e43 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f5f9e8734c8190a214685b1647abe1 |
completed | May 2, 2026, 1:19 p.m. |
| PD | Predicate disambiguation | batch_69f5afec3e94819080d9ba86cf8c866e |
completed | May 2, 2026, 8:03 a.m. |
| PDg | Predicate description generation | batch_69f5f6b32a8881909baa0db57b80d56a |
completed | May 2, 2026, 1:05 p.m. |
Created at: April 21, 2026, 5:01 p.m.