Triple
T31661144
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hurricanes (Super Rugby) |
E808003
|
entity |
| Predicate | typicalStyleOfPlay |
P3775
|
FINISHED |
| Object | expansive backline play |
—
|
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: expansive backline play | Statement: [Hurricanes (Super Rugby), typicalStyleOfPlay, expansive backline play]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalStyleOfPlay Context triple: [Hurricanes (Super Rugby), typicalStyleOfPlay, expansive backline play]
-
A.
styleOfPlay
chosen
Indicates the characteristic manner or approach in which an entity performs or behaves, especially in a game, sport, or artistic context.
-
B.
typeOfPlayStrength
Indicates the relative intensity or power level with which a play or move is executed or characterized.
-
C.
associatedWithStyleOfPlayOfBearer
Indicates that something is connected to or characterized by the style of play exhibited by the bearer.
-
D.
isTypicallyPlayed
Indicates that an activity, game, or sport is commonly engaged in or performed by a particular type of participant or group.
-
E.
typicalPlayingPosition
Indicates the usual role or position an entity regularly occupies when participating in a game, sport, or similar activity.
- 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_69f348daf95c81908b4c985b7ddcd0b3 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_6a037c894b488190bcbec2eccaff4a01 |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379e7aa0c8190bdc9ee4d54fc821b |
completed | May 12, 2026, 7:05 p.m. |
Created at: April 30, 2026, 10:57 p.m.