Triple
T35107874
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lindwurm (dragon) |
E1013200
|
entity |
| Predicate | roleInHeraldry |
P111971
|
FINISHED |
| Object | supporter |
—
|
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: supporter | Statement: [Lindwurm (dragon), roleInHeraldry, supporter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInHeraldry Context triple: [Lindwurm (dragon), roleInHeraldry, supporter]
-
A.
coatOfArms
Indicates that one entity serves as the heraldic emblem or coat of arms representing another entity.
-
B.
heraldicName
Indicates the formal name or designation assigned to a heraldic element (such as a coat of arms, charge, or symbol) within a heraldic system.
-
C.
notableHerald
Indicates that one entity is a herald (messenger or announcer) of particular significance or prominence in relation to another entity.
-
D.
heraldicAspect
chosen
Indicates a relationship where one entity serves as a heraldic feature, attribute, or component in the coat of arms or heraldic representation of another entity.
-
E.
heraldicConnection
Indicates a relationship where entities are linked through heraldry, such as by shared coats of arms, heraldic symbols, lineage, or official armorial associations.
- 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_69f76dd659d08190bcdc00d37caafb62 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a0120f070b081909b6d1a3d8ee6b80e |
completed | May 11, 2026, 12:21 a.m. |
| PD | Predicate disambiguation | batch_6a01209da37481909683e38f264b15ef |
completed | May 11, 2026, 12:19 a.m. |
Created at: May 3, 2026, 4:01 p.m.