Triple
T24564635
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2005 British & Irish Lions tour to New Zealand |
E607747
|
entity |
| Predicate | testSeriesOpponent |
P106971
|
FINISHED |
| Object | New Zealand All Blacks |
—
|
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: New Zealand All Blacks | Statement: [2005 British & Irish Lions tour to New Zealand, testSeriesOpponent, New Zealand All Blacks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: testSeriesOpponent Context triple: [2005 British & Irish Lions tour to New Zealand, testSeriesOpponent, New Zealand All Blacks]
-
A.
teamOpponent
chosen
Indicates that two teams are competing against each other as opponents in a game or match.
-
B.
recordOpponent
Indicates that one entity is documented or registered as the opposing party or competitor of another entity.
-
C.
opponentStarPlayerTeam
Indicates that the referenced team is the one for which the opponent’s star player plays.
-
D.
associatedOpponent
Indicates that one entity is recognized or designated as an opponent or adversary associated with another entity in a given context.
-
E.
wasOpponentOf
Indicates that one entity competed or conflicted against another as an adversary in some contest, game, or confrontation.
- 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_69e2c4cc35a48190990b7571bc086df8 |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2a8f9d0f881909afc04537c32f76b |
completed | April 30, 2026, 12:57 a.m. |
| PD | Predicate disambiguation | batch_69f2a6b99e7c8190ba7e2dc8729a314a |
completed | April 30, 2026, 12:47 a.m. |
Created at: April 18, 2026, 2:28 a.m.