Triple
T29736572
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tassadar |
E752476
|
entity |
| Predicate | learnsTechnique |
P110076
|
FINISHED |
| Object | Dark Templar void energies |
—
|
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: Dark Templar void energies | Statement: [Tassadar, learnsTechnique, Dark Templar void energies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: learnsTechnique Context triple: [Tassadar, learnsTechnique, Dark Templar void energies]
-
A.
learnsSkill
chosen
Indicates that an entity acquires or develops a particular skill through learning or practice.
-
B.
hasTechnique
Indicates that an entity employs, utilizes, or is associated with a particular method, procedure, or technique.
-
C.
demonstratedTechniqueFocus
Indicates that an entity has shown or highlighted a particular technique as the main focus of its demonstration.
-
D.
skillTaught
Indicates that one entity teaches or imparts a particular skill to another entity.
-
E.
trainingMethod
Indicates the specific approach, technique, or procedure used to train an entity (such as a person, model, or system).
- 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_69f0d62a36a88190bf860f00da433ff8 |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f673344cf88190855d66b73e45cb5d |
completed | May 2, 2026, 9:57 p.m. |
| PD | Predicate disambiguation | batch_69f66ac1a4fc81909740d2e52fbe6970 |
completed | May 2, 2026, 9:21 p.m. |
Created at: April 28, 2026, 7:45 p.m.