Triple
T12519585
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint Patrick's Battalion |
E299279
|
entity |
| Predicate | leaderNationality |
P105423
|
FINISHED |
| Object | Irish |
—
|
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 | Statement: [Saint Patrick's Battalion, leaderNationality, Irish]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leaderNationality Context triple: [Saint Patrick's Battalion, leaderNationality, Irish]
-
A.
originCountryLeader
Indicates that one entity is the political leader (e.g., head of state or government) of the country from which the other entity originates.
-
B.
hasCountryLeader
Indicates that a specified country is led or governed by a particular leader (such as a president, prime minister, or monarch).
-
C.
countryLeaderOf
Indicates that one entity serves as the head of state or government of the specified country.
-
D.
governmentLeader
Indicates that one entity serves as the primary political head or chief executive authority of the other entity (typically a state, region, or governmental body).
-
E.
countryLeaderAssociated
Indicates that there is a notable connection or involvement between a country’s leader and another entity, without specifying a formal role or specific type of relationship.
- 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_69d6ada5cdd48190860d9ce30aff69be |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d954b867dc8190af8a70f797e4d133 |
completed | April 10, 2026, 7:51 p.m. |
| PD | Predicate disambiguation | batch_69d954096af88190b6be81b008c82139 |
completed | April 10, 2026, 7:48 p.m. |
| PDg | Predicate description generation | batch_69d954b715fc819091fa84430be46273 |
completed | April 10, 2026, 7:51 p.m. |
Created at: April 8, 2026, 9:57 p.m.