Triple
T21940093
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eesti vapp |
E541793
|
entity |
| Predicate | heraldilineTüüp |
P111971
|
FINISHED |
| Object | kilp |
—
|
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: kilp | Statement: [Eesti vapp, heraldilineTüüp, kilp]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heraldilineTüüp Context triple: [Eesti vapp, heraldilineTüüp, kilp]
-
A.
heralds
Indicates that one event, action, or entity serves as a sign or forerunner announcing the imminent arrival or occurrence of another.
-
B.
notableHerald
Indicates that one entity is a herald (messenger or announcer) of particular significance or prominence in relation to another entity.
-
C.
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.
-
D.
heraldicDivision
Indicates the way a heraldic shield or field is partitioned into distinct sections or areas.
-
E.
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.
- 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_69e0c47e2e5c81909a7f74ce3de50911 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f12420b1cc81909b375891aedc0979 |
completed | April 28, 2026, 9:18 p.m. |
| PD | Predicate disambiguation | batch_69e6f5efc208819091ed2cf6841fa600 |
completed | April 21, 2026, 3:58 a.m. |
Created at: April 16, 2026, 7:55 p.m.