Triple
T30146954
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Royal Air Force peaked cap |
E766281
|
entity |
| Predicate | hasInsigniaDepicting |
P21497
|
FINISHED |
| Object | eagle and crown motif |
—
|
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: eagle and crown motif | Statement: [Royal Air Force peaked cap, hasInsigniaDepicting, eagle and crown motif]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasInsigniaDepicting Context triple: [Royal Air Force peaked cap, hasInsigniaDepicting, eagle and crown motif]
-
A.
hasInsigniaComponent
Indicates that an entity includes, bears, or is composed of a particular insignia or emblem as one of its components.
-
B.
hasInsigniaWornBy
Indicates that a particular insignia is worn by a specified entity (such as a person, group, or organization).
-
C.
hasDistinctiveEmblem
Indicates that an entity possesses a unique symbol, logo, or emblem that serves to distinguish it from others.
-
D.
symbolOnInsignia
chosen
Indicates that a particular symbol appears on or is featured as part of an insignia.
-
E.
hasTypeOfInsignia
Indicates that an entity bears or is associated with a specific kind or category of insignia.
- 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_69f2247909048190ae86c2160cf8b566 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fec5c503808190bde0b1829ea43071 |
completed | May 9, 2026, 5:27 a.m. |
| PD | Predicate disambiguation | batch_69fec535dd6c8190a6ab85201f5a04a9 |
completed | May 9, 2026, 5:25 a.m. |
Created at: April 29, 2026, 7:19 p.m.