Triple
T29655123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Archon |
E750242
|
entity |
| Predicate | canAttack |
P143292
|
FINISHED |
| Object | ground units |
—
|
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: ground units | Statement: [Archon, canAttack, ground units]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canAttack Context triple: [Archon, canAttack, ground units]
-
A.
hasAttack
Indicates that one entity performs, possesses, or is associated with an attack directed toward another entity.
-
B.
attackFeasibility
Indicates the extent to which carrying out an attack is practically possible given current conditions, capabilities, and constraints.
-
C.
canTarget
chosen
Indicates that one entity is able or permitted to select, aim at, or direct its action or effect toward another entity as a target.
-
D.
canKill
Indicates that one entity has the ability or potential to cause the death of another entity.
-
E.
hasBaseAttack
Indicates that an entity possesses a fundamental or default attack action or value used as its primary offensive capability.
- 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_69f6659f246081909821c5f452d14e8f |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 28, 2026, 6:54 p.m.