Triple
T31110674
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Academic Ranking of World Universities |
E792935
|
entity |
| Predicate | rankingFrequency |
P51026
|
FINISHED |
| Object | annual |
—
|
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: annual | Statement: [Academic Ranking of World Universities, rankingFrequency, annual]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rankingFrequency Context triple: [Academic Ranking of World Universities, rankingFrequency, annual]
-
A.
selectionRankingFrequency
Indicates how often an entity is chosen or ranked in a particular position within a selection or ordering process.
-
B.
rankingUsage
Indicates how an entity is used or positioned within an ordered ranking or hierarchy relative to others.
-
C.
rankingScope
Indicates the context or domain within which a ranking is defined, interpreted, or applied.
-
D.
rankingImpact
Indicates how an entity’s position or level in a ranking is affected or influenced by another factor or action.
-
E.
rankingUpdateFrequency
chosen
Indicates how often the ranking or ordered list associated with an entity is recalculated or refreshed.
- 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_69f224cfd5d881908ec6447bc321cd58 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f757898fe48190b124dc7301672623 |
completed | May 3, 2026, 2:11 p.m. |
| PD | Predicate disambiguation | batch_69f754c484348190948d2a04ff228fb1 |
completed | May 3, 2026, 1:59 p.m. |
Created at: April 29, 2026, 9:04 p.m.