Triple
T4313896
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anne de Breuil |
E94140
|
entity |
| Predicate | hasMark |
P2130
|
FINISHED |
| Object | fleur-de-lis branded on her shoulder |
—
|
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: fleur-de-lis branded on her shoulder | Statement: [Anne de Breuil, hasMark, fleur-de-lis branded on her shoulder]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMark Context triple: [Anne de Breuil, hasMark, fleur-de-lis branded on her shoulder]
-
A.
hasMarker
chosen
Indicates that one entity possesses, is associated with, or is identified by a specific marker.
-
B.
usedMark
Indicates that one entity has employed or applied a particular mark, symbol, or indicator in some context or action.
-
C.
hasCaseMarking
Indicates that a linguistic element (such as a noun or pronoun) bears a specific grammatical case marking that signals its syntactic or semantic role in a clause.
-
D.
hasMarketingIcon
Indicates that an entity is associated with, or represented by, a specific marketing-related icon or symbol.
-
E.
marksOn
Indicates that one entity bears visible signs, traces, or imprints that have been made or left by another 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_69b3451886588190a3dd1305ea7c58dc |
completed | March 12, 2026, 10:58 p.m. |
| NER | Named-entity recognition | batch_69b350f319c08190bb40a9fc5933728d |
completed | March 12, 2026, 11:49 p.m. |
| PD | Predicate disambiguation | batch_69b34f4a07b08190a06ada0d9cbb14fb |
completed | March 12, 2026, 11:42 p.m. |
Created at: March 12, 2026, 11:12 p.m.