Triple
T6926046
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Colbán, Earl of Fife |
E160311
|
entity |
| Predicate | titlePrecedence |
P35573
|
FINISHED |
| Object | premier earl of Scotland |
—
|
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: premier earl of Scotland | Statement: [Colbán, Earl of Fife, titlePrecedence, premier earl of Scotland]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: titlePrecedence Context triple: [Colbán, Earl of Fife, titlePrecedence, premier earl of Scotland]
-
A.
titleHierarchy
chosen
Indicates a hierarchical relationship between titles, where one title is ranked above or below another in an ordered structure.
-
B.
titleVariant
Indicates that one title is an alternative or variant form of another title referring to the same work or entity.
-
C.
titles
Indicates that one entity holds a formal title, designation, or name associated with another entity.
-
D.
titleStart
Indicates that one entity’s title begins with the text or substring represented by the other entity.
-
E.
titlePattern
Indicates that there is a specific structural or textual pattern that the title of an entity is expected to follow.
- 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_69c6884d350081908d8a970e4d40ad78 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6da1aa9c48190b63a04be2ed9e266 |
completed | March 27, 2026, 7:27 p.m. |
| PD | Predicate disambiguation | batch_69c6d7bb577c81908ee8b415b4281f3d |
completed | March 27, 2026, 7:17 p.m. |
Created at: March 27, 2026, 2:27 p.m.