Triple
T16114295
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arms of the Richelieu family |
E390962
|
entity |
| Predicate | languageOfHeraldry |
P9680
|
FINISHED |
| Object | French heraldry |
—
|
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: French heraldry | Statement: [Arms of the Richelieu family, languageOfHeraldry, French heraldry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageOfHeraldry Context triple: [Arms of the Richelieu family, languageOfHeraldry, French heraldry]
-
A.
languageOfHistoricalBlazon
Indicates the language in which a historical blazon (a formal heraldic description) is written or recorded.
-
B.
notableHerald
Indicates that one entity is a herald (messenger or announcer) of particular significance or prominence in relation to another entity.
-
C.
coatOfArmsMotto
Indicates the phrase or motto that appears on or is officially associated with a particular coat of arms.
-
D.
coatOfArms
Indicates that one entity serves as the heraldic emblem or coat of arms representing another entity.
-
E.
heraldicTradition
chosen
Indicates a relationship where something belongs to, follows, or is characterized by a particular system or style of heraldic customs and practices.
- 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_69d87f1a8dd881909f1de6ef78849874 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e20169ce488190bbc814f23a3b7547 |
completed | April 17, 2026, 9:46 a.m. |
| PD | Predicate disambiguation | batch_69e1828518c48190a8ef3aaa46a1f639 |
completed | April 17, 2026, 12:44 a.m. |
Created at: April 10, 2026, 5 a.m.