Triple
T37662825
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Snow Golem |
E937753
|
entity |
| Predicate | targetingAI |
P196509
|
FINISHED |
| Object | targets most nearby hostile mobs |
—
|
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: targets most nearby hostile mobs | Statement: [Snow Golem, targetingAI, targets most nearby hostile mobs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: targetingAI Context triple: [Snow Golem, targetingAI, targets most nearby hostile mobs]
-
A.
target
Indicates that one entity is the intended object, goal, or focus of another entity’s action or attention.
-
B.
targetedAdversary
chosen
Indicates that one entity deliberately selects and focuses hostile or competitive actions on another specific entity.
-
C.
targetsSystems
Indicates that an entity is directed at, attacks, or is intended to affect specific systems.
-
D.
targetsVector
Indicates that one entity is directed toward, aimed at, or focused on another entity represented as a vector (e.g., a direction or target position).
-
E.
aimsToCapture
Indicates an intention or effort by one entity to take control of, seize, or gain possession of another entity.
- 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_69f76ed6df7c8190b018e5baea716ceb |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ff409ff5548190849c2d50e99bd807 |
completed | May 9, 2026, 2:11 p.m. |
| PD | Predicate disambiguation | batch_69ff401a5e188190a72f945e910b4a6c |
completed | May 9, 2026, 2:09 p.m. |
Created at: May 3, 2026, 4:18 p.m.