Triple
T12718248
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IBF heavyweight title |
E303904
|
entity |
| Predicate | minimumWeight |
P76140
|
FINISHED |
| Object | over 200 pounds (90.7 kg) |
—
|
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: over 200 pounds (90.7 kg) | Statement: [IBF heavyweight title, minimumWeight, over 200 pounds (90.7 kg)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: minimumWeight Context triple: [IBF heavyweight title, minimumWeight, over 200 pounds (90.7 kg)]
-
A.
minimumMass
chosen
Indicates the smallest mass value that an entity or system is required, allowed, or observed to have within a given context.
-
B.
minimumDegree
Indicates that the relationship specifies the smallest number of connections or edges incident to any entity within a given structure or set.
-
C.
maximumWeight
Indicates the greatest allowable or observed weight value associated with an entity or relationship.
-
D.
minimumNumber
Indicates that the associated value is the smallest or least quantity allowed, required, or observed within a given set or context.
-
E.
minimalNorm
Indicates that among a set of possible values or solutions, this one has the smallest norm (magnitude) according to a specified norm measure.
- 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_69d7bdf084148190ab9d513dc0735af4 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9625d9da48190ab377f9328a0e1f5 |
completed | April 10, 2026, 8:49 p.m. |
| PD | Predicate disambiguation | batch_69d960c088dc8190b0e63312c54e4c6c |
completed | April 10, 2026, 8:42 p.m. |
Created at: April 9, 2026, 5:23 p.m.