Triple
T20416185
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rosaline |
E500717
|
entity |
| Predicate | relationshipToPrincessOfFrance |
P89053
|
FINISHED |
| Object | attendant |
—
|
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: attendant | Statement: [Rosaline, relationshipToPrincessOfFrance, attendant]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipToPrincessOfFrance Context triple: [Rosaline, relationshipToPrincessOfFrance, attendant]
-
A.
relationshipToElizabethOfValois
Indicates a specified familial, marital, or social relationship that one entity has to Elizabeth of Valois.
-
B.
relationshipToPrincess
chosen
Indicates the specific familial, social, or romantic connection that one entity has to a princess.
-
C.
relationshipToCharlesV
Indicates the specific familial or social relationship that one entity has to Charles V.
-
D.
relationshipTypeWith Queen Anne of Austria
Indicates the specific nature or category of relational connection an entity has with Queen Anne of Austria (e.g., familial, political, or social relationship).
-
E.
royalAssociation
Indicates a relationship in which an entity is connected or linked to royalty, a royal person, or a royal institution.
- 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_69e0b4a935588190b9446a99b37ced44 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67a4437448190b07b6e6e3de5830f |
completed | April 20, 2026, 7:11 p.m. |
| PD | Predicate disambiguation | batch_69e5766df0008190a73c4f613c29678f |
completed | April 20, 2026, 12:42 a.m. |
Created at: April 16, 2026, 11:30 a.m.