Triple
T24274682
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WBA light middleweight title |
E605374
|
entity |
| Predicate | weightRangeBelow |
P26162
|
FINISHED |
| Object | 160 pounds (middleweight limit) |
—
|
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: 160 pounds (middleweight limit) | Statement: [WBA light middleweight title, weightRangeBelow, 160 pounds (middleweight limit)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: weightRangeBelow Context triple: [WBA light middleweight title, weightRangeBelow, 160 pounds (middleweight limit)]
-
A.
weightClassBelow
Indicates that one entity belongs to a lower (lighter) weight class than another entity.
-
B.
weightRangeDescription
chosen
Indicates the textual description that specifies the range within which an entity’s weight falls.
-
C.
weightCondition
Indicates that a specified weight-related requirement or constraint holds between entities or values.
-
D.
wasBelow
Indicates that one entity was positioned at a lower level or altitude than another entity at a given time.
-
E.
liesBelow
Indicates that one entity is positioned at a lower vertical level than another entity.
- 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_69e2954707dc8190915551eb114cfff6 |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f28d5da53c8190810f4e7777d112ba |
completed | April 29, 2026, 10:59 p.m. |
| PD | Predicate disambiguation | batch_69f1c457a2908190993824395b3c365d |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 18, 2026, 12:07 a.m.