Triple
T71883
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Irish American |
E1437
|
entity |
| Predicate | diasporaRelation |
P2103
|
FINISHED |
| Object | Irish diaspora |
—
|
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: Irish diaspora | Statement: [Irish American, diasporaRelation, Irish diaspora]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: diasporaRelation Context triple: [Irish American, diasporaRelation, Irish diaspora]
-
A.
hasDiaspora
chosen
Indicates that a group, community, or population has members who have dispersed or settled outside their original homeland or region.
-
B.
relatedEthnicGroup
Indicates that there is a notable ethnic connection or association between two ethnic groups, such as shared ancestry, culture, or historical ties.
-
C.
wasColonyOf
Indicates that one entity functioned as a colony under the political control or administration of another entity.
-
D.
relatedCountry
Indicates that there is a relevant or associated relationship between an entity and a specified country, without specifying the exact nature of that relationship.
-
E.
foreignRelationsManagedBy
Indicates that the responsibility for conducting or overseeing a party’s foreign relations is held by a specified managing entity.
- 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_69a24c06b3bc8190aa4ac89026115efc |
completed | Feb. 28, 2026, 1:59 a.m. |
| NER | Named-entity recognition | batch_69a24f6997c081908b202f937eb2b14f |
completed | Feb. 28, 2026, 2:14 a.m. |
| PD | Predicate disambiguation | batch_69a24eab7f408190a8275cb82474f575 |
completed | Feb. 28, 2026, 2:10 a.m. |
Created at: Feb. 28, 2026, 2:03 a.m.