Triple
T30708992
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Countess de Premilly (disputed/claimed) |
E781836
|
entity |
| Predicate | claimantNationality |
P133856
|
FINISHED |
| Object | American |
—
|
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: American | Statement: [Countess de Premilly (disputed/claimed), claimantNationality, American]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: claimantNationality Context triple: [Countess de Premilly (disputed/claimed), claimantNationality, American]
-
A.
nationalityClaimedAs
chosen
Indicates that an entity asserts or is recorded as having a particular nationality, regardless of its legal or factual status.
-
B.
plaintiffNationality
Indicates that a person or entity in the role of plaintiff has a specified national affiliation or citizenship.
-
C.
countryOfClaim
Indicates the country in which a claim (such as legal, insurance, or patent claim) is formally filed or asserted.
-
D.
ownerNationality
Indicates that the owner of an entity has the specified nationality.
-
E.
bearerNationality
Indicates that one entity is the country or nationality associated with the bearer of another entity, such as a document or credential.
- 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_69f224abfcf081909492e64d3cc35262 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f739a638748190808e7a2930dce16e |
completed | May 3, 2026, 12:03 p.m. |
| PD | Predicate disambiguation | batch_69f732f2dc6c8190a4e86da98cc5eb05 |
completed | May 3, 2026, 11:35 a.m. |
Created at: April 29, 2026, 8:35 p.m.