Triple
T2147172
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Graham Henry |
E47093
|
entity |
| Predicate | hasTrained |
P36609
|
FINISHED |
| Object | numerous All Blacks internationals |
—
|
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: numerous All Blacks internationals | Statement: [Graham Henry, hasTrained, numerous All Blacks internationals]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTrained Context triple: [Graham Henry, hasTrained, numerous All Blacks internationals]
-
A.
hasTrainingType
Indicates that an entity is associated with or characterized by a specific type or category of training.
-
B.
trainedAs
Indicates that one entity has received education or instruction to perform the role, profession, or function represented by another entity.
-
C.
requiresTraining
Indicates that one entity can only be properly or legitimately used, performed, or engaged with if the other entity has first received appropriate training.
-
D.
hasBeginnerFriendlyTraining
Indicates that an entity provides training or instructional resources suitable for beginners or those with little prior experience.
-
E.
trainingModel
Indicates that an entity is engaged in the process of teaching, adjusting, or optimizing a model using data or experience.
- 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_69a88a1933e0819094f18426ed74180f |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abbeaa14bc81908486683decd7ae42 |
completed | March 7, 2026, 5:59 a.m. |
| PD | Predicate disambiguation | batch_69abbd9846e88190b6c2941dd9ce7749 |
completed | March 7, 2026, 5:54 a.m. |
| PDg | Predicate description generation | batch_69abbea8bd4881908f72019a5acf6174 |
completed | March 7, 2026, 5:59 a.m. |
Created at: March 4, 2026, 7:44 p.m.