Triple
T36280622
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cook Islands national rugby union team |
E892928
|
entity |
| Predicate | hasSevensVariant |
P58794
|
FINISHED |
| Object | Cook Islands national rugby sevens team |
—
|
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: Cook Islands national rugby sevens team | Statement: [Cook Islands national rugby union team, hasSevensVariant, Cook Islands national rugby sevens team]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSevensVariant Context triple: [Cook Islands national rugby union team, hasSevensVariant, Cook Islands national rugby sevens team]
-
A.
playsSevensVariant
Indicates that an entity participates in or engages in a sevens variant of a game or sport.
-
B.
hasCardGameVariant
Indicates that one game is a variation or modified form of another card game.
-
C.
hasSevensTeam
chosen
Indicates that an entity is associated with or has a designated team participating in rugby sevens.
-
D.
sevensSide
Indicates that one entity is on the side associated with the number seven relative to another entity or reference frame.
-
E.
usesSevenGameSeries
Indicates that a competition or playoff round is structured as a best-of-seven game series to determine the winner.
- 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_69f76e4955c08190b8cfddca34fc0242 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a004c41f13c8190bc47daf6a5ca3949 |
completed | May 10, 2026, 9:13 a.m. |
| PD | Predicate disambiguation | batch_6a004bce3e3081909b35ae5b3bf2b35e |
completed | May 10, 2026, 9:11 a.m. |
Created at: May 3, 2026, 4:09 p.m.