Triple
T31804708
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Victory Bell (Duke–North Carolina) rivalry |
E811840
|
entity |
| Predicate | trophyColorWhenDukeWins |
P41239
|
FINISHED |
| Object | Duke blue and white |
—
|
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: Duke blue and white | Statement: [Victory Bell (Duke–North Carolina) rivalry, trophyColorWhenDukeWins, Duke blue and white]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: trophyColorWhenDukeWins Context triple: [Victory Bell (Duke–North Carolina) rivalry, trophyColorWhenDukeWins, Duke blue and white]
-
A.
trophyColor
chosen
Indicates the color attribute assigned to a trophy in the relationship.
-
B.
winnerColor
Indicates the color associated with the entity that wins in a given event or competition.
-
C.
trophyWonBy
Indicates that a particular trophy or award is obtained or earned by a specific entity (such as a person or team).
-
D.
trophy
Indicates that one entity is a trophy awarded or possessed in relation to another entity, typically as a result of winning or achieving something.
-
E.
trophyWonWith
Indicates that a particular trophy or award was achieved using, through, or in association with a specified means, tool, team, or context.
- 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_69f348e70d188190b4637c5509f81274 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6b21e7e088190832a3db585daea1c |
completed | May 3, 2026, 2:25 a.m. |
| PD | Predicate disambiguation | batch_69f6b14faf608190a25b977c0740729c |
completed | May 3, 2026, 2:22 a.m. |
Created at: April 30, 2026, 11:42 p.m.