Triple
T650294
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Royal Air Force heraldry |
E11331
|
entity |
| Predicate | usesSymbolType |
P13707
|
FINISHED |
| Object | roundels |
—
|
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: roundels | Statement: [Royal Air Force heraldry, usesSymbolType, roundels]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesSymbolType Context triple: [Royal Air Force heraldry, usesSymbolType, roundels]
-
A.
symbolType
chosen
Indicates the classification or category of a symbol based on its role, form, or function within a given system.
-
B.
symbolicallyUses
Indicates that one entity employs another as a symbol or representation to convey meaning, ideas, or associations rather than for its literal or practical function.
-
C.
hasSymbolNamedAfter
Indicates that one entity has a symbol whose name is derived from or dedicated to another entity.
-
D.
hasTraditionalSymbol
Indicates that something is associated with or represented by a conventional or culturally established symbol.
-
E.
usedInSignatureOf
Indicates that something (such as a type, parameter, or construct) appears as part of the formal signature of a function, method, or similar callable 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_69a493266a2881909daf4c40f719dee8 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49f31e70c81909a2ac1d939f7ec07 |
completed | March 1, 2026, 8:18 p.m. |
| PD | Predicate disambiguation | batch_69a49d0eade081909c47e85ed55f808d |
completed | March 1, 2026, 8:09 p.m. |
Created at: March 1, 2026, 7:36 p.m.