Triple
T29655449
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dark Shrine |
E750250
|
entity |
| Predicate | targetPlayer |
P111154
|
FINISHED |
| Object | Protoss player |
—
|
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: Protoss player | Statement: [Dark Shrine, targetPlayer, Protoss player]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: targetPlayer Context triple: [Dark Shrine, targetPlayer, Protoss player]
-
A.
targetUserPosition
Indicates the spatial position or location of a specified user relative to a reference frame or environment.
-
B.
targetOfPlayerReaction
Indicates that an entity is the object or focus toward which a player's reaction is directed.
-
C.
target
Indicates that one entity is the intended object, goal, or focus of another entity’s action or attention.
-
D.
targetOwner
Indicates that one entity is the owner or primary possessor of a specified target entity.
-
E.
targetUnit
chosen
Indicates that one entity serves as the specific unit or object that another entity is directed at, operates on, or is intended to affect.
- 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_69fd05ba6b2c81909c62b46237d10365 |
completed | May 7, 2026, 9:35 p.m. |
| PD | Predicate disambiguation | batch_69fd03039e48819082b6e12c5453885a |
completed | May 7, 2026, 9:24 p.m. |
Created at: April 28, 2026, 6:55 p.m.