Triple
T33347825
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IRB Junior Player of the Year |
E853847
|
entity |
| Predicate | formerNameOfPresenter |
P200900
|
FINISHED |
| Object | International Rugby Board |
—
|
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: International Rugby Board | Statement: [IRB Junior Player of the Year, formerNameOfPresenter, International Rugby Board]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerNameOfPresenter Context triple: [IRB Junior Player of the Year, formerNameOfPresenter, International Rugby Board]
-
A.
formerName
Indicates that an entity was previously known by a different name in the past.
-
B.
formerMemberName
Indicates that the referenced name belongs to an entity that was previously a member of a particular group, organization, or body but is no longer one.
-
C.
promotionFormerName
Indicates that an entity previously operated or was known under a different promotion name before adopting its current one.
-
D.
formerNameOfDesigner
Indicates that one entity was previously the name used by a designer before being changed to a new name.
-
E.
predecessorName
Indicates that the value is the name of an entity that directly precedes another in an ordered sequence or lineage.
- 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_69f3496a1a588190bad9cbe9221144e0 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69ffb82be8148190a1c870d467a28c80 |
completed | May 9, 2026, 10:41 p.m. |
| PD | Predicate disambiguation | batch_69ffb7bbd550819094052e9a0d0ae320 |
completed | May 9, 2026, 10:39 p.m. |
| PDg | Predicate description generation | batch_69ffb82b40788190bf401344a3f288dd |
completed | May 9, 2026, 10:41 p.m. |
Created at: May 1, 2026, 1:34 a.m.