Triple
T16755506
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Caitlín Brugha |
E407196
|
entity |
| Predicate | stoodDown |
P124517
|
FINISHED |
| Object | June 1927 Irish general election |
—
|
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: June 1927 Irish general election | Statement: [Caitlín Brugha, stoodDown, June 1927 Irish general election]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stoodDown Context triple: [Caitlín Brugha, stoodDown, June 1927 Irish general election]
-
A.
down
Indicates that one entity is located at a lower position or level relative to another entity or reference point.
-
B.
wasBelow
Indicates that one entity was positioned at a lower level or altitude than another entity at a given time.
-
C.
under
Indicates that one entity is positioned below or beneath another entity, often implying vertical alignment or coverage.
-
D.
laidDown
Indicates that an entity places or sets another entity down into a resting or horizontal position.
-
E.
downSpecial
Indicates that an entity performs or is associated with a special action or ability triggered by a downward input or downward-directed command.
- 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_69d8839174188190909f190097207065 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3abe831ec8190bac05b07db6153c1 |
completed | April 18, 2026, 4:06 p.m. |
| PD | Predicate disambiguation | batch_69e319cbd79c8190a03587a61c18bec0 |
completed | April 18, 2026, 5:42 a.m. |
| PDg | Predicate description generation | batch_69e326bac94481908c082117553320f8 |
completed | April 18, 2026, 6:37 a.m. |
Created at: April 10, 2026, 5:21 a.m.