Triple
T33835121
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Antoine Hastoy |
E867209
|
entity |
| Predicate | typeOfUnionCode |
P202938
|
FINISHED |
| Object | rugby union |
—
|
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: rugby union | Statement: [Antoine Hastoy, typeOfUnionCode, rugby union]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfUnionCode Context triple: [Antoine Hastoy, typeOfUnionCode, rugby union]
-
A.
typeOfUnion
Indicates the specific kind or category of union relationship that exists between the related entities.
-
B.
codeUnitType
Indicates the specific kind or category of a code unit (such as a file, class, method, or module) that a given element belongs to.
-
C.
codeType
Indicates the classification or category assigned to a particular code within a coding or encoding system.
-
D.
forceTypeUnion
Indicates that multiple possible types are combined into a single union type, allowing a value or entity to conform to any one of those types.
-
E.
unificationType
Indicates the specific manner or category in which two or more entities are combined, merged, or treated as a single unified whole.
- 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_69f34992ad40819087760ed939bd2a7a |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a00d24043e8819090cc473b6c0923d0 |
completed | May 10, 2026, 6:45 p.m. |
| PD | Predicate disambiguation | batch_6a00d1ec12fc81908c514ed088ef8300 |
completed | May 10, 2026, 6:43 p.m. |
| PDg | Predicate description generation | batch_6a00d23f402c8190bf49c0d4cce10b73 |
completed | May 10, 2026, 6:45 p.m. |
Created at: May 1, 2026, 1:47 a.m.