Triple
T26274653
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | First Period architecture |
E660528
|
entity |
| Predicate | chimneyPlacement |
P160190
|
FINISHED |
| Object | central chimney |
—
|
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: central chimney | Statement: [First Period architecture, chimneyPlacement, central chimney]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: chimneyPlacement Context triple: [First Period architecture, chimneyPlacement, central chimney]
-
A.
chimneyStatus
Indicates the operational or physical condition of a chimney, such as whether it is functional, damaged, blocked, or inactive.
-
B.
heightOfChimney
Indicates the vertical measurement of a chimney from its base to its top.
-
C.
hasChimneyCount
Indicates the number of chimneys that an entity possesses or is associated with.
-
D.
hasChimneys
Indicates that one entity possesses or is equipped with one or more chimneys.
-
E.
hasFireplace
Indicates that one entity possesses or is equipped with a fireplace.
- 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_69ee812960d081909cff6085cc9fa3a6 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f60e33c5748190abaa09d9b0c4c00a |
completed | May 2, 2026, 2:46 p.m. |
| PD | Predicate disambiguation | batch_69f5f7ff548c8190a23e98c5e66e0bc7 |
completed | May 2, 2026, 1:11 p.m. |
| PDg | Predicate description generation | batch_69f5ffc6268c8190b63f6360ebadab73 |
completed | May 2, 2026, 1:44 p.m. |
Created at: April 26, 2026, 9:54 p.m.