Triple
T29655060
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Void Ray |
E750241
|
entity |
| Predicate | techTier |
P2086
|
FINISHED |
| Object | mid–late tech Protoss unit |
—
|
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: mid–late tech Protoss unit | Statement: [Void Ray, techTier, mid–late tech Protoss unit]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: techTier Context triple: [Void Ray, techTier, mid–late tech Protoss unit]
-
A.
technicalGrade
Indicates the level or classification of technical quality, complexity, or proficiency assigned to something.
-
B.
technologyLevel
chosen
Indicates the degree of technological advancement or sophistication associated with an entity relative to others or to a defined scale.
-
C.
technologyLevelComparedTo
Indicates how the technological advancement of one entity compares relative to that of another entity.
-
D.
technicalRating
Indicates the level or quality of technical proficiency, complexity, or performance associated with an entity.
-
E.
teamLevel
Indicates the hierarchical rank or tier at which a team operates within an organization, competition, or structure.
- 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_69f0d6226fe881908819197c9ef9ee04 |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f66f274ba08190bcdbdfeccf4af09d |
completed | May 2, 2026, 9:39 p.m. |
| PD | Predicate disambiguation | batch_69f66abfdaf08190a55f14c70be6fd4d |
completed | May 2, 2026, 9:21 p.m. |
Created at: April 28, 2026, 6:54 p.m.