Triple
T3176961
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mumtaz Mahal |
E66486
|
entity |
| Predicate | relationToNurJahan |
P45667
|
FINISHED |
| Object | niece |
—
|
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: niece | Statement: [Mumtaz Mahal, relationToNurJahan, niece]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationToNurJahan Context triple: [Mumtaz Mahal, relationToNurJahan, niece]
-
A.
servedAsLadyInWaitingTo
Indicates that one person held the role of lady-in-waiting in service to another, typically a female member of royalty or nobility.
-
B.
historicalRelationship
Indicates a relationship that existed between entities in the past, often tied to a specific historical period, context, or event.
-
C.
associatedHeir
Indicates that one entity is designated or recognized as the heir connected to, or inheriting from, another entity.
-
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.
daughterOf
Indicates that one person is the female child (daughter) of another person.
- F. None of above. chosen
Provenance (4 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_69ad8586a34c8190944c63ec11a8de1a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada69b0bec8190957913b44d876079 |
completed | March 8, 2026, 4:40 p.m. |
| PD | Predicate disambiguation | batch_69ad9e02677c8190a21d93b1259b2761 |
completed | March 8, 2026, 4:04 p.m. |
| PDg | Predicate description generation | batch_69ada0f7c21c819087e9992f5fe30a37 |
completed | March 8, 2026, 4:16 p.m. |
Created at: March 8, 2026, 3:06 p.m.