Triple
T24564657
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2005 British & Irish Lions tour to New Zealand |
E607747
|
entity |
| Predicate | replacementTestSeriesCaptain |
P156363
|
FINISHED |
| Object | Gareth Thomas |
—
|
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: Gareth Thomas | Statement: [2005 British & Irish Lions tour to New Zealand, replacementTestSeriesCaptain, Gareth Thomas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: replacementTestSeriesCaptain Context triple: [2005 British & Irish Lions tour to New Zealand, replacementTestSeriesCaptain, Gareth Thomas]
-
A.
numberOfTestsAsCaptain
Indicates the total count of test matches in which an entity served in the role of captain.
-
B.
testMatchesAsCaptain
Indicates that the subject participated in matches specifically in the role or capacity of a captain.
-
C.
alternateCaptain
Indicates that an entity serves as the designated secondary team leader or substitute captain for another entity (typically a sports team).
-
D.
teamCaptain
Indicates that one entity serves as the captain or designated leader of a particular team.
-
E.
odiWinsAsCaptain
Indicates that the person, serving as captain in a One Day International (ODI) cricket match, led the team to a victory.
- F. None of above. chosen
Provenance (4 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. |
| PDg | Predicate description generation | batch_69f2a846c5bc81909ba50cee483bea91 |
completed | April 30, 2026, 12:54 a.m. |
Created at: April 18, 2026, 2:28 a.m.