Triple
T814082
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Romanesque architecture |
E17610
|
entity |
| Predicate | doorwayType |
P8655
|
FINISHED |
| Object | deeply recessed portals |
—
|
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: deeply recessed portals | Statement: [Romanesque architecture, doorwayType, deeply recessed portals]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: doorwayType Context triple: [Romanesque architecture, doorwayType, deeply recessed portals]
-
A.
doorType
chosen
Indicates the specific kind or category of door associated with an entity.
-
B.
doorConfiguration
Indicates how a door is arranged or set up in relation to its frame, opening direction, and operational characteristics.
-
C.
doorLocation
Indicates the spatial position or placement of a door relative to a reference structure or area.
-
D.
hasEntranceOn
Indicates that one entity’s entrance or access point is located on or faces a specified side, boundary, or feature of another entity.
-
E.
hasEntrance
Indicates that one entity possesses or provides an entry point or access way to another entity or space.
- 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_69a4937bcaac8190a322524ac6f45a5a |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4ab5035608190bff5f3843b75e662 |
completed | March 1, 2026, 9:10 p.m. |
| PD | Predicate disambiguation | batch_69a4aa756920819080ae82948974c876 |
completed | March 1, 2026, 9:07 p.m. |
Created at: March 1, 2026, 7:38 p.m.