Triple
T647335
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prince Andrew, Duke of York |
E11268
|
entity |
| Predicate | positionInSiblingOrder |
P5163
|
FINISHED |
| Object | second son of Queen Elizabeth II |
—
|
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: second son of Queen Elizabeth II | Statement: [Prince Andrew, Duke of York, positionInSiblingOrder, second son of Queen Elizabeth II]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionInSiblingOrder Context triple: [Prince Andrew, Duke of York, positionInSiblingOrder, second son of Queen Elizabeth II]
-
A.
positionInHierarchy
chosen
Indicates that one entity occupies a specific rank or level relative to another within an ordered hierarchy.
-
B.
siblingCount
Indicates the number of siblings an entity has.
-
C.
isPositionOf
Indicates that one entity represents the spatial or organizational position or location of another entity.
-
D.
positionInState
Indicates that one entity occupies or holds a specific position, role, or status within a particular state or condition of another entity.
-
E.
positionInTrackList
Indicates the specific ordered place an item occupies within a track list.
- 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_69a493266a2881909daf4c40f719dee8 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49f1cb24481909d3b41a56b29dee9 |
completed | March 1, 2026, 8:18 p.m. |
| PD | Predicate disambiguation | batch_69a49d0c0dcc8190849211d45489a5a7 |
completed | March 1, 2026, 8:09 p.m. |
Created at: March 1, 2026, 7:36 p.m.