Triple
T21020976
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Avellaneda derby |
E517804
|
entity |
| Predicate | featuresCompetitionLevel |
P142499
|
FINISHED |
| Object | top division football |
—
|
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: top division football | Statement: [Avellaneda derby, featuresCompetitionLevel, top division football]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresCompetitionLevel Context triple: [Avellaneda derby, featuresCompetitionLevel, top division football]
-
A.
featuredCompetitionLevel
Indicates that a particular competition level is highlighted or given special prominence relative to other levels.
-
B.
featuresCompetitionIn
Indicates that something includes or presents a particular competition as part of its content or structure.
-
C.
competitionLevelOf
Indicates the degree or intensity of competitiveness associated with an entity, event, or context.
-
D.
fifaCompetitionLevel
Indicates the level or tier of a FIFA-sanctioned competition in which an entity participates or to which it belongs.
-
E.
competitionLevel
Indicates the degree or intensity of competitive pressure or rivalry present in a given context or interaction.
- F. None of above. chosen
Provenance (4 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_69e0b50262b081909bc488937145eb73 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fc5db0b88190ae61ea8b38e8ecf7 |
completed | April 21, 2026, 4:26 a.m. |
| PD | Predicate disambiguation | batch_69e5dbf274ac81909bbf245627dc8fdc |
completed | April 20, 2026, 7:55 a.m. |
| PDg | Predicate description generation | batch_69e5e2df1a888190b5b478e76bdf7fdf |
completed | April 20, 2026, 8:25 a.m. |
Created at: April 16, 2026, 1:54 p.m.