Triple
T969692
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Government of Ireland Act 1920 |
E20917
|
entity |
| Predicate | numberOfCountiesInSouthernIreland |
P22533
|
FINISHED |
| Object | 26 |
—
|
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: 26 | Statement: [Government of Ireland Act 1920, numberOfCountiesInSouthernIreland, 26]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfCountiesInSouthernIreland Context triple: [Government of Ireland Act 1920, numberOfCountiesInSouthernIreland, 26]
-
A.
islandCounty
Indicates that a county is located on, or primarily consists of, one or more islands.
-
B.
shireCounty
Indicates the county-level administrative area (shire county) within which a given place or entity is located or governed.
-
C.
hasNumberOfConstituencies
Indicates the specific count of constituencies associated with an entity.
-
D.
includesCounty
Indicates that a larger geographic or administrative region contains or encompasses a specific county within its boundaries.
-
E.
bordersCountyAcrossWater
Indicates that one county is separated from and adjacent to another county by a body of water rather than by land.
- 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_69a493b33d2c81909c52c369d3ca8436 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4b4497d688190b59c3a195e377080 |
completed | March 1, 2026, 9:48 p.m. |
| PD | Predicate disambiguation | batch_69a4b2a579888190afb489ac9fe8391c |
completed | March 1, 2026, 9:41 p.m. |
| PDg | Predicate description generation | batch_69a4b385176081909e3e8c3f647c1fd4 |
completed | March 1, 2026, 9:45 p.m. |
Created at: March 1, 2026, 7:40 p.m.