Triple
T24375848
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Earls of Montrose |
E614471
|
entity |
| Predicate | titleHolderBranch |
P142566
|
FINISHED |
| Object | leading branch of Clan Graham |
—
|
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: leading branch of Clan Graham | Statement: [Earls of Montrose, titleHolderBranch, leading branch of Clan Graham]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: titleHolderBranch Context triple: [Earls of Montrose, titleHolderBranch, leading branch of Clan Graham]
-
A.
titleHolderHouseBranch
chosen
Indicates the specific branch of a house or family line that currently holds or is associated with a given title.
-
B.
titleHolderUnder
Indicates that one entity holds a title, position, or rank under the authority, jurisdiction, or hierarchy of another entity.
-
C.
titleHolderIs
Indicates that one entity currently holds or possesses a specific title associated with another entity.
-
D.
titleHolderWas
Indicates that an entity previously held a specific title or position before it passed to someone or something else.
-
E.
titleHolderChild
Indicates that one entity is the child of another entity who holds a specific title or position.
- 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_69e2d7e1e010819098b95eb3f905943d |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f293d73c0c8190b80e257845a04c57 |
completed | April 29, 2026, 11:27 p.m. |
| PD | Predicate disambiguation | batch_69f287bb1b2c81909c2e7fcc392ad143 |
completed | April 29, 2026, 10:35 p.m. |
Created at: April 18, 2026, 2:02 a.m.