Triple
T30839568
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2014 FIFA World Cup quarter-final match |
E785462
|
entity |
| Predicate | belongsToEdition |
P51901
|
FINISHED |
| Object | 20th FIFA World Cup |
—
|
NE NERFINISHED |
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: 20th FIFA World Cup | Statement: [2014 FIFA World Cup quarter-final match, belongsToEdition, 20th FIFA World Cup]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: belongsToEdition Context triple: [2014 FIFA World Cup quarter-final match, belongsToEdition, 20th FIFA World Cup]
-
A.
associatedWithEdition
chosen
Indicates a relationship where something is linked or connected to a specific edition of a work or resource.
-
B.
hasEditionRelationship
Indicates a relationship where one resource is an edition or version of another, linking different manifestations of essentially the same work.
-
C.
hasEditionRole
Indicates that an entity holds a specific editorial role or responsibility in relation to a particular edition of a work.
-
D.
hasEditionIn
Indicates that one entity has a specific edition or version that exists or is available in another entity (such as a particular format, language, or location).
-
E.
hasEditionType
Indicates that one entity is a specific edition type or format classification of another entity (such as a work, publication, or product).
- 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_69f224b73d8c81908129383bfb397c87 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fe349879848190bcd77e3cc3470458 |
completed | May 8, 2026, 7:08 p.m. |
| PD | Predicate disambiguation | batch_69fe31e3cf908190b23ebc2f7fe58722 |
completed | May 8, 2026, 6:56 p.m. |
Created at: April 29, 2026, 8:45 p.m.