Triple
T23673786
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shimazu clan |
E584809
|
entity |
| Predicate | familyCrest |
P92259
|
FINISHED |
| Object | cross in a circle (Shimazu mon) |
—
|
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: cross in a circle (Shimazu mon) | Statement: [Shimazu clan, familyCrest, cross in a circle (Shimazu mon)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: familyCrest Context triple: [Shimazu clan, familyCrest, cross in a circle (Shimazu mon)]
-
A.
emblemFamily
Indicates that one emblem belongs to, represents, or is associated with a particular family or familial lineage.
-
B.
clanCrestAssociatedWith
chosen
Indicates that a particular clan crest is symbolically or traditionally linked to a specific clan or family.
-
C.
hasHeraldicFamily
Indicates that an entity is associated with a particular heraldic family or lineage, typically sharing the same coat of arms or heraldic identity.
-
D.
familyNameIn
Indicates that an entity has a specified family name (surname) in a particular language or cultural context.
-
E.
familyDesignation
Indicates the specific familial role or relationship label assigned to one entity in relation to another (e.g., parent, sibling, child).
- 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_69e24901421881908c17a5293bdd4a8e |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b4f1dee08190bfe78564c65f01ad |
completed | April 29, 2026, 7:36 a.m. |
| PD | Predicate disambiguation | batch_69f118dd13008190a8799b4e9cadbd79 |
completed | April 28, 2026, 8:30 p.m. |
Created at: April 17, 2026, 6:51 p.m.