Triple
T2726873
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Countess of Snowdon |
E60213
|
entity |
| Predicate | peerageRankOfSpouse |
P37264
|
FINISHED |
| Object | earl |
—
|
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: earl | Statement: [Countess of Snowdon, peerageRankOfSpouse, earl]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: peerageRankOfSpouse Context triple: [Countess of Snowdon, peerageRankOfSpouse, earl]
-
A.
rankRelativeToPeerage
Indicates how an entity’s hierarchical rank compares to that of a specified peer or peer group within a defined ranking system.
-
B.
rankInBritishPeerageSystem
Indicates the specific noble title or level an entity holds within the hierarchical structure of the British peerage system.
-
C.
marriedToRank
chosen
Indicates that one entity is married to another entity who holds a specific rank or position.
-
D.
typeOfPeerage
Indicates the specific rank or category within a system of peerage that a given title or noble status belongs to.
-
E.
peerageSystem
Indicates a hierarchical system of noble ranks and titles that defines relative status and privileges among members of a nobility.
- 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_69ab4b75cd908190b691ef0d1801acda |
completed | March 6, 2026, 9:47 p.m. |
| NER | Named-entity recognition | batch_69abdace9f308190964a064859612cd6 |
completed | March 7, 2026, 7:59 a.m. |
| PD | Predicate disambiguation | batch_69abd82586f88190a98f60d3247fe2d3 |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:56 p.m.