Triple
T1665321
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Houses of Parliament series |
E35996
|
entity |
| Predicate | seriesTheme |
P7671
|
FINISHED |
| Object | changing light over architecture |
—
|
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: changing light over architecture | Statement: [Houses of Parliament series, seriesTheme, changing light over architecture]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: seriesTheme Context triple: [Houses of Parliament series, seriesTheme, changing light over architecture]
-
A.
seriesType
Indicates the classification or category of a series that an entity belongs to or is associated with.
-
B.
theme
Indicates the entity that is the primary participant or content affected or characterized by an action, event, or state.
-
C.
themeFor
Indicates that something serves as the central subject, topic, or focus for another thing (such as an event, work, or activity).
-
D.
seriesLeader
Indicates that one entity serves as the primary leader, head, or main responsible figure for a particular series involving another entity.
-
E.
notableTheme
chosen
Indicates that a particular theme is prominently featured in, or strongly associated with, an entity such as a work, event, or body of content.
- 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_69a8861286808190939afff3ce8ee31e |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aa994f92b0819084ee2f6a672334b9 |
completed | March 6, 2026, 9:07 a.m. |
| PD | Predicate disambiguation | batch_69a907d2475c8190b7ec7dccd3335eb1 |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:29 p.m.