Triple
T29893610
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | the Empire |
E759217
|
entity |
| Predicate | primaryMilitaryAsset |
P110549
|
FINISHED |
| Object | Imperial Star Destroyer |
E1031297
|
NE 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: Imperial Star Destroyer | Statement: [the Empire, primaryMilitaryAsset, Imperial Star Destroyer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryMilitaryAsset Context triple: [the Empire, primaryMilitaryAsset, Imperial Star Destroyer]
-
A.
enemyMilitaryAsset
Indicates that one entity is a military asset belonging to or controlled by an enemy force relative to the other entity.
-
B.
isMilitaryAssetOf
chosen
Indicates that something functions as a military resource, equipment, or facility that belongs to, is controlled by, or is used by a particular entity.
-
C.
eraOfPrimaryMilitaryUse
Indicates the historical time period during which the subject was primarily used for military purposes.
-
D.
militaryCharacteristic
Indicates that one entity possesses a specific military-related attribute, quality, or feature in relation to another entity or context.
-
E.
militaryUse
Indicates the use of something (such as land, facilities, equipment, or resources) for military purposes or operations.
- F. None of above.
Provenance (4 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_69f2245f1cf88190978c70d1a1d2cb73 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_6a01a9e333fc819087d583ff319be0b3 |
completed | May 11, 2026, 10:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a26f1e1e30c8190ac523575779904e9 |
completed | June 8, 2026, 4:46 p.m. |
| PD | Predicate disambiguation | batch_6a01a877c9e08190b0678618d3533286 |
completed | May 11, 2026, 9:59 a.m. |
Created at: April 29, 2026, 6:03 p.m.