Triple
T1082894
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ACT |
E23985
|
entity |
| Predicate | scoreReporting |
P10741
|
FINISHED |
| Object | composite score |
—
|
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: composite score | Statement: [ACT, scoreReporting, composite score]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scoreReporting Context triple: [ACT, scoreReporting, composite score]
-
A.
scoreReportedTo
chosen
Indicates that a score or result has been communicated or submitted from one party to another.
-
B.
scoreScale
Indicates the scale or range on which a score or rating is expressed or measured.
-
C.
scoring
Indicates the act of achieving points or a measurable result, typically by successfully completing an action that contributes to a score or outcome.
-
D.
isScoreFor
Indicates that one value represents the score or result associated with a particular entity, event, or performance.
-
E.
statusQualificationMetric
Indicates a metric that qualifies, evaluates, or characterizes the status or condition of something in a measurable way.
- 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_69a493f1ddf48190a99d54b00e99f8ce |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b95e56948190a1e92367ad7240b7 |
completed | March 1, 2026, 10:10 p.m. |
| PD | Predicate disambiguation | batch_69a4b73f4310819086281f8ec67d1a32 |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:42 p.m.