Triple
T4764793
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Queen Elizabeth The Queen Mother |
E105780
|
entity |
| Predicate | stepRelation |
P59182
|
FINISHED |
| Object | mother-in-law of Prince Philip, Duke of Edinburgh |
—
|
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: mother-in-law of Prince Philip, Duke of Edinburgh | Statement: [Queen Elizabeth The Queen Mother, stepRelation, mother-in-law of Prince Philip, Duke of Edinburgh]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stepRelation Context triple: [Queen Elizabeth The Queen Mother, stepRelation, mother-in-law of Prince Philip, Duke of Edinburgh]
-
A.
datumRelation
Indicates a relationship where one piece of data is connected to, derived from, or otherwise associated with another piece of data.
-
B.
valueRelation
Indicates a comparative or associative relationship between the values or magnitudes of two or more entities.
-
C.
semanticRelation
Indicates a general meaning-based connection between two entities, such as similarity, implication, or conceptual association.
-
D.
titleRelation
Indicates a relationship where one entity serves as the title, designation, or formal name associated with another entity.
-
E.
successorRelationship
Indicates a relationship where one entity directly follows or replaces another in a sequence, order, or role.
- 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_69bd43f226fc8190b867cc249c2a9042 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd686ef1b08190ad60375592c9d6c0 |
completed | March 20, 2026, 3:31 p.m. |
| PD | Predicate disambiguation | batch_69bd622807f881908e4bcb14f7731bac |
completed | March 20, 2026, 3:05 p.m. |
| PDg | Predicate description generation | batch_69bd686dc7b88190b41e8a362701080d |
completed | March 20, 2026, 3:31 p.m. |
Created at: March 20, 2026, 1:21 p.m.