Triple
T29654275
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terran |
E750225
|
entity |
| Predicate | coreAirUnit |
P24170
|
FINISHED |
| Object | Viking |
—
|
NE NERFINISHED |
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: Viking | Statement: [Terran, coreAirUnit, Viking]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coreAirUnit Context triple: [Terran, coreAirUnit, Viking]
-
A.
aerialUnit
chosen
Indicates that the related entity functions as or is classified as an aerial unit, typically operating or acting in the air rather than on the ground or sea.
-
B.
alliedAirUnit
Indicates that an air unit is friendly or allied to the reference side or force.
-
C.
airborneForces
Indicates that military forces are deployed, transported, or operating via aircraft, typically inserted from the air into an operational area.
-
D.
airCommander
Indicates that an entity serves as the commanding officer or leader of air forces or air operations for another entity.
-
E.
typicalAviationCombatElement
Indicates that one entity is a standard or characteristic component, unit, or formation used in aviation combat operations relative to 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_69f0d6226fe881908819197c9ef9ee04 |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f66f269b908190a8a5f65bac23f083 |
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.