Triple
T27341032
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Earl of Galloway |
E690098
|
entity |
| Predicate | lowerTitlePossible |
P93156
|
FINISHED |
| Object | Viscount |
—
|
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: Viscount | Statement: [Earl of Galloway, lowerTitlePossible, Viscount]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lowerTitlePossible Context triple: [Earl of Galloway, lowerTitlePossible, Viscount]
-
A.
lowerOrEqualRankTitle
chosen
Indicates that one entity’s rank or title is lower than or equal to the rank or title of another entity.
-
B.
higherTitleOf
Indicates that one entity holds a job or position title that is hierarchically superior to the title held by another entity.
-
C.
mayBeTitled
Indicates that an entity can optionally bear or be assigned a particular title, but is not required to have it.
-
D.
lowered
Indicates that one entity caused another entity’s level, value, position, or intensity to become less than it was before.
-
E.
titleVariant
Indicates that one title is an alternative or variant form of another title referring to the same work or entity.
- 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_69ef355e5b388190a8fc1eba9b4a6656 |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f62ad30b1c8190abe2c8f0c10c1a8a |
completed | May 2, 2026, 4:48 p.m. |
| PD | Predicate disambiguation | batch_69f620e4b1c88190a17940251abc68fd |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 11:42 a.m.