Triple
T6571419
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marie-Anne de Bourbon, Mademoiselle de Blois |
E155447
|
entity |
| Predicate | rankAtCourt |
P62203
|
FINISHED |
| Object | princess of the blood |
—
|
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: princess of the blood | Statement: [Marie-Anne de Bourbon, Mademoiselle de Blois, rankAtCourt, princess of the blood]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rankAtCourt Context triple: [Marie-Anne de Bourbon, Mademoiselle de Blois, rankAtCourt, princess of the blood]
-
A.
courtRank
chosen
Indicates the formal hierarchical rank or status an individual holds within a court or courtly system.
-
B.
defendantRank
Indicates the hierarchical position or status assigned to a defendant relative to other defendants in a legal case.
-
C.
roleAtCourt
Indicates the specific position, function, or status an entity holds within a court or courtly setting.
-
D.
courtOfficial
Indicates that an entity serves in an official capacity within a court, holding an authorized role in judicial or legal proceedings.
-
E.
heldCourtUnder
Indicates that one authority conducted judicial or ceremonial court proceedings under the jurisdiction, auspices, or authority of another.
- 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_69c688151254819080387f87deab8fa7 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6cc9c6cb0819084fec8e0beb430de |
completed | March 27, 2026, 6:29 p.m. |
| PD | Predicate disambiguation | batch_69c6acf93cb48190b54f5dd6febd34dc |
completed | March 27, 2026, 4:14 p.m. |
Created at: March 27, 2026, 1:53 p.m.