Triple
T863236
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Democratic Unionist Party |
E18642
|
entity |
| Predicate | stanceOnSameSexMarriage |
P3468
|
FINISHED |
| Object | opposes same-sex marriage (historically) |
—
|
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: opposes same-sex marriage (historically) | Statement: [Democratic Unionist Party, stanceOnSameSexMarriage, opposes same-sex marriage (historically)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stanceOnSameSexMarriage Context triple: [Democratic Unionist Party, stanceOnSameSexMarriage, opposes same-sex marriage (historically)]
-
A.
hasPositionOnHomosexuality
chosen
Indicates that an entity holds a specific stance, view, or policy regarding homosexuality.
-
B.
religiousStatus
Indicates the religious affiliation, role, or standing that an entity holds within a religious context.
-
C.
marriageType
Indicates the specific legal or social category of a marriage relationship that exists between two spouses.
-
D.
suffrage
Indicates that an entity has the right or privilege to vote in political or organizational decision-making processes.
-
E.
legalStatusOfElectors
Indicates the legal standing, rights, and recognition granted to electors under applicable laws or regulations.
- 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_69a4938ce8688190a24bdfef82ba7d21 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4ac67d4d481909487d3edb3e46936 |
completed | March 1, 2026, 9:15 p.m. |
| PD | Predicate disambiguation | batch_69a4aa86065881909d477e26fdd84d45 |
completed | March 1, 2026, 9:07 p.m. |
Created at: March 1, 2026, 7:39 p.m.