Triple
T35315127
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chief of Clan Donnachaidh |
E1019881
|
entity |
| Predicate | clanCrestBadge |
P117273
|
FINISHED |
| Object | Right hand upholding an imperial crown |
—
|
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: Right hand upholding an imperial crown | Statement: [Chief of Clan Donnachaidh, clanCrestBadge, Right hand upholding an imperial crown]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: clanCrestBadge Context triple: [Chief of Clan Donnachaidh, clanCrestBadge, Right hand upholding an imperial crown]
-
A.
clanCrestAssociatedWith
Indicates that a particular clan crest is symbolically or traditionally linked to a specific clan or family.
-
B.
hasClanSymbol
chosen
Indicates that an entity is associated with a particular clan through a specific identifying symbol.
-
C.
protectiveEmblemName
Indicates that a given name is the designated title or label of a protective emblem associated with an entity or context.
-
D.
coatOfArms
Indicates that one entity serves as the heraldic emblem or coat of arms representing another entity.
-
E.
sharesClanBadgeWith
Indicates that two entities possess and display the same clan badge, signifying shared clan affiliation or membership.
- 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_69f76de9d45c81908a2ed0956b448b65 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f79090c29c81909172903f1c5d82c8 |
completed | May 3, 2026, 6:14 p.m. |
| PD | Predicate disambiguation | batch_69f78e2f52e08190a77661223a96c601 |
completed | May 3, 2026, 6:04 p.m. |
Created at: May 3, 2026, 4:03 p.m.