Triple
T12443555
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Buster Douglas |
E297337
|
entity |
| Predicate | upsetRanking |
P46779
|
FINISHED |
| Object | one of the biggest upsets in boxing history |
—
|
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: one of the biggest upsets in boxing history | Statement: [Buster Douglas, upsetRanking, one of the biggest upsets in boxing history]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: upsetRanking Context triple: [Buster Douglas, upsetRanking, one of the biggest upsets in boxing history]
-
A.
upset
Indicates that one entity causes another to feel distressed, unhappy, or emotionally disturbed.
-
B.
formerRanking
Indicates that an entity previously held a particular rank or position but no longer does so.
-
C.
peakRanking
Indicates the highest position or rank an entity has ever achieved within a specified ranking system or context.
-
D.
impactOnStandings
chosen
Indicates how an event or outcome affects the relative rankings or standings within a competition or system.
-
E.
maintainsRanking
Indicates that one entity preserves or keeps another entity’s position or level within a ranking or ordered list.
- 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_69d6ada166c48190b902972cd2408fa3 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d95151e7348190a1d4953a8b416a13 |
completed | April 10, 2026, 7:36 p.m. |
| PD | Predicate disambiguation | batch_69d94d3c27a08190a0237200203e476d |
completed | April 10, 2026, 7:19 p.m. |
Created at: April 8, 2026, 9:55 p.m.