Triple
T19097791
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Forbes of Pitsligo |
E467451
|
entity |
| Predicate | coatOfArmsRelation |
P1663
|
FINISHED |
| Object | arms of Clan Forbes |
—
|
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: arms of Clan Forbes | Statement: [Forbes of Pitsligo, coatOfArmsRelation, arms of Clan Forbes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coatOfArmsRelation Context triple: [Forbes of Pitsligo, coatOfArmsRelation, arms of Clan Forbes]
-
A.
coatOfArms
chosen
Indicates that one entity serves as the heraldic emblem or coat of arms representing another entity.
-
B.
coatOfArmsType
Indicates the specific kind or category of coat of arms associated with an entity.
-
C.
heraldicConnection
Indicates a relationship where entities are linked through heraldry, such as by shared coats of arms, heraldic symbols, lineage, or official armorial associations.
-
D.
coatOfArmsCaption
Indicates the descriptive text that explains or labels the depicted coat of arms.
-
E.
replacedOnCoatOfArmsBy
Indicates that one element or symbol on a coat of arms has been superseded and taken the place of by another element or symbol.
- 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_69d8dd05ac4c8190b1967d8f97f3fb2f |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e36b279c819091a8d51f044bc644 |
completed | April 20, 2026, 8:27 a.m. |
| PD | Predicate disambiguation | batch_69e4b9ac41848190afd0f33b42cebe99 |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 12:04 p.m.