Triple
T23847215
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Destroyer Squadron 10 |
E592055
|
entity |
| Predicate | usedFlagshipType |
P36594
|
FINISHED |
| Object | light cruiser |
—
|
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: light cruiser | Statement: [Destroyer Squadron 10, usedFlagshipType, light cruiser]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedFlagshipType Context triple: [Destroyer Squadron 10, usedFlagshipType, light cruiser]
-
A.
hasFlagshipIn
Indicates that an entity designates a particular location or branch as its primary or flagship presence.
-
B.
hasFlagshipType
Indicates that an entity has a primary or leading type within a set of related types.
-
C.
isFlagshipServiceOf
Indicates that a particular service is the primary, leading, or most prominent offering of a given organization or provider.
-
D.
flagshipType
chosen
Indicates that one entity is the primary or most important representative (flagship) of a particular type, category, or group defined by the other entity.
-
E.
hasFlagshipSpecies
Indicates that one entity (typically a site, region, or conservation program) is associated with or represented by a particular flagship species used to promote awareness or protection.
- 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_69e25d221d908190b9b502ad31e66a3f |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c88c9bbc81909204120279e6d980 |
completed | April 29, 2026, 8:59 a.m. |
| PD | Predicate disambiguation | batch_69f1614612b481908c45d99e588882f9 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:10 p.m.