Triple
T37204463
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brian Hook |
E922128
|
entity |
| Predicate | programmingSpecialty |
P22526
|
FINISHED |
| Object | real-time 3D graphics |
—
|
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: real-time 3D graphics | Statement: [Brian Hook, programmingSpecialty, real-time 3D graphics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: programmingSpecialty Context triple: [Brian Hook, programmingSpecialty, real-time 3D graphics]
-
A.
programmingFocus
chosen
Indicates a relationship where an entity’s primary attention, effort, or specialization is directed toward a particular area or aspect of programming.
-
B.
programmingCategory
Indicates that one entity is classified as a programming-related category or type for the other entity.
-
C.
technicalSpecialty
Indicates that an entity has expertise or specialized knowledge in a particular technical field or domain.
-
D.
programmingIncludes
Indicates that one programming-related entity contains, incorporates, or makes use of another as a part, feature, or component.
-
E.
programmingCharacteristic
Indicates a relationship where an entity possesses or exhibits a particular property, trait, or quality specifically related to programming.
- 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_69f76ea4849481909b4a3073efb0114c |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb55de3b9c8190a7656aeab3c3ffbc |
completed | May 6, 2026, 2:53 p.m. |
| PD | Predicate disambiguation | batch_69fb35bc92e08190bff447624e2df791 |
completed | May 6, 2026, 12:36 p.m. |
Created at: May 3, 2026, 4:15 p.m.