Triple
T30766086
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arms of the Duke of Hamilton |
E783375
|
entity |
| Predicate | rankOfTitle |
P90523
|
FINISHED |
| Object | premier duke in the Peerage 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 duke in the Peerage of Scotland | Statement: [Arms of the Duke of Hamilton, rankOfTitle, premier duke in the Peerage of Scotland]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rankOfTitle Context triple: [Arms of the Duke of Hamilton, rankOfTitle, premier duke in the Peerage of Scotland]
-
A.
rankOfHead
Indicates the hierarchical level or status assigned to the head (leader) of an entity within an ordered ranking system.
-
B.
hasRankOrTitle
chosen
Indicates that an entity holds, is assigned, or is associated with a specific rank, title, or formal designation.
-
C.
lowerOrEqualRankTitle
Indicates that one entity’s rank or title is lower than or equal to the rank or title of another entity.
-
D.
useRankTitles
Indicates that rank-based titles are applied or displayed for the entities involved.
-
E.
scoreTitle
Indicates the title or label associated with a particular score or scoring instance.
- 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_69f224b047f48190b4f5efeb7ee97b37 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f68fbe1b2881909ca26a21f9e67ddc |
completed | May 2, 2026, 11:58 p.m. |
| PD | Predicate disambiguation | batch_69f686140aa08190a35f62572b2db9b6 |
completed | May 2, 2026, 11:17 p.m. |
Created at: April 29, 2026, 8:40 p.m.