Triple
T827706
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vox |
E17891
|
entity |
| Predicate | politicalPositionOnSameSexMarriage |
P4795
|
FINISHED |
| Object | opposes same-sex marriage |
—
|
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 | Statement: [Vox, politicalPositionOnSameSexMarriage, opposes same-sex marriage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: politicalPositionOnSameSexMarriage Context triple: [Vox, politicalPositionOnSameSexMarriage, opposes same-sex marriage]
-
A.
hasPositionOnHomosexuality
Indicates that an entity holds a specific stance, view, or policy regarding homosexuality.
-
B.
policyStance
chosen
Indicates the position or viewpoint an entity holds regarding a specific policy or set of policies.
-
C.
sexualOrientation
Indicates an entity’s enduring pattern of romantic or sexual attraction toward others, typically in terms of the genders or sexes to which it is attracted.
-
D.
politicalIdentity
Indicates the political affiliation, ideology, or stance that characterizes an entity’s position within a political spectrum or system.
-
E.
constitutionalPosition
Indicates the official role, office, or status an entity holds within a constitutional or legal framework.
- 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_69a4937c9c188190aaa216f6b466f452 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4ab99b1e48190afad1f073348b29a |
completed | March 1, 2026, 9:11 p.m. |
| PD | Predicate disambiguation | batch_69a4aa79a6488190a634388e071ed9b7 |
completed | March 1, 2026, 9:07 p.m. |
Created at: March 1, 2026, 7:38 p.m.