Triple
T28933095
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carnegie family of Angus |
E733839
|
entity |
| Predicate | hasHereditaryPeers |
P1913
|
FINISHED |
| Object | Earl of Southesk |
—
|
NE NERFINISHED |
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: Earl of Southesk | Statement: [Carnegie family of Angus, hasHereditaryPeers, Earl of Southesk]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHereditaryPeers Context triple: [Carnegie family of Angus, hasHereditaryPeers, Earl of Southesk]
-
A.
hereditaryPeersIncluded
Indicates that hereditary peers are counted as part of the specified group, body, or arrangement.
-
B.
hasHereditaryChief
Indicates that an entity is led or governed by a chief whose position is inherited through family lineage.
-
C.
hasHereditaryNumber
Indicates that an entity is associated with a specific hereditary identifier or sequence number passed down through a lineage or inheritance chain.
-
D.
hereditaryPeerage
chosen
Indicates that a person holds a noble title that is legally inheritable and passes down through family lineage.
-
E.
hasHereditaryOffice
Indicates that an entity holds an office or position that is passed down through family lineage rather than acquired by election, appointment, or merit.
- 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_69f05b0b49b08190b8994b339c7980f6 |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69f760a35b988190904e6267553ad2fe |
completed | May 3, 2026, 2:50 p.m. |
| PD | Predicate disambiguation | batch_69f75eb3d6f081908c933474eb359e3d |
completed | May 3, 2026, 2:41 p.m. |
Created at: April 28, 2026, 8:29 a.m.