Triple
T6618821
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duchess of Saxony |
E149622
|
entity |
| Predicate | precedenceUnder |
P13059
|
FINISHED |
| Object | queens within the realm |
—
|
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: queens within the realm | Statement: [Duchess of Saxony, precedenceUnder, queens within the realm]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: precedenceUnder Context triple: [Duchess of Saxony, precedenceUnder, queens within the realm]
-
A.
confersPrecedenceIn
Indicates that one entity is granted higher priority, rank, or standing over another within a specified context or domain.
-
B.
hasLowerPrecedenceThan
chosen
Indicates that one item is ranked or ordered with a lower priority or importance compared to another item.
-
C.
subordinateTo
Indicates that one entity holds a lower rank, status, or authority and is subject to the control, direction, or oversight of another entity.
-
D.
orderPrecedence
Indicates that one entity must come before another in a defined sequence or priority order.
-
E.
sharesPrecedenceWith
Indicates that two entities occupy the same level in an ordering or hierarchy, such that neither has priority or precedence over the other.
- 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_69c687ed8a9c81908bb671717cb192ef |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6bdb88cc881908f35648c15a7dc85 |
completed | March 27, 2026, 5:26 p.m. |
| PD | Predicate disambiguation | batch_69c6ad007c1c8190af425f51011c7ad1 |
completed | March 27, 2026, 4:14 p.m. |
Created at: March 27, 2026, 1:58 p.m.