Triple
T13484685
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Charles Armstrong-Jones, Viscount Linley |
E318464
|
entity |
| Predicate | paternalTitleConnection |
P110578
|
FINISHED |
| Object | heir apparent to the Earldom of Snowdon |
—
|
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: heir apparent to the Earldom of Snowdon | Statement: [Charles Armstrong-Jones, Viscount Linley, paternalTitleConnection, heir apparent to the Earldom of Snowdon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: paternalTitleConnection Context triple: [Charles Armstrong-Jones, Viscount Linley, paternalTitleConnection, heir apparent to the Earldom of Snowdon]
-
A.
fatherTitle
Indicates the formal title or designation held by a person's father.
-
B.
relationshipWithFather
Indicates a familial relationship that specifically connects an individual to their father.
-
C.
patriarchTitle
Indicates that one entity holds the role or title of patriarch in relation to another entity.
-
D.
paternalHouse
Indicates the family house or lineage associated with a person's father.
-
E.
paternalRelationshipStatusToZerubbabel
Indicates the specific paternal relationship or status that one entity has in relation to Zerubbabel.
- F. None of above. chosen
Provenance (4 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_69d806b6bfec819089222715b2e86c8e |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dbaf3a15b48190b63fb59e926a97ae |
completed | April 12, 2026, 2:42 p.m. |
| PD | Predicate disambiguation | batch_69dbae06061881909a6a6032e0507587 |
completed | April 12, 2026, 2:36 p.m. |
| PDg | Predicate description generation | batch_69dbaecc98cc8190829f5be759c4f1e3 |
completed | April 12, 2026, 2:40 p.m. |
Created at: April 9, 2026, 9:42 p.m.