Triple
T24944470
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | super welterweight |
E624148
|
entity |
| Predicate | adjacentLowerClass |
P36307
|
FINISHED |
| Object | welterweight |
—
|
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: welterweight | Statement: [super welterweight, adjacentLowerClass, welterweight]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: adjacentLowerClass Context triple: [super welterweight, adjacentLowerClass, welterweight]
-
A.
adjacentRouteLower
Indicates that one route is directly adjacent to another route that is positioned at a lower level or elevation.
-
B.
adjacentLandmark
Indicates that one landmark is located directly next to or very near another landmark, with no significant separation between them.
-
C.
classBelow
chosen
Indicates that one class is positioned lower than another in a hierarchy, ordering, or structural arrangement.
-
D.
adjacentLine
Indicates that one line is directly next to another line, sharing a common boundary or position without overlapping.
-
E.
isAdjacentTo
Indicates that one entity is directly next to or bordering another without anything of the same type in between.
- 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_69e2ff22e4c48190a0444b5a044f14e8 |
completed | April 18, 2026, 3:48 a.m. |
| NER | Named-entity recognition | batch_69f48b9b687881908fd87a2f5fa0b1e7 |
completed | May 1, 2026, 11:16 a.m. |
| PD | Predicate disambiguation | batch_69f48060597c8190a4414e4e4fcb1fec |
completed | May 1, 2026, 10:28 a.m. |
Created at: April 18, 2026, 5:53 a.m.