Triple
T12875708
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cathedral |
E307959
|
entity |
| Predicate | centralScene |
P107401
|
FINISHED |
| Object | the narrator and Robert draw a cathedral together |
—
|
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: the narrator and Robert draw a cathedral together | Statement: [Cathedral, centralScene, the narrator and Robert draw a cathedral together]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: centralScene Context triple: [Cathedral, centralScene, the narrator and Robert draw a cathedral together]
-
A.
centralLocation
Indicates that one entity serves as the primary or central place associated with another entity.
-
B.
centralIn
Indicates that one entity occupies a central or most important position within another entity, context, or structure.
-
C.
centralWork
Indicates that a particular work is the primary, most important, or focal work associated with an entity or context.
-
D.
centralEntity
Indicates that the subject serves as the primary or most important entity around which related entities, actions, or information are organized.
-
E.
centerType
Indicates the classification or category of a center (e.g., type of facility, institution, or hub) associated with an entity.
- 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_69d7bdf69bc48190af6c2621f28ca351 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97c7f91d08190aac2f6419d3ba992 |
completed | April 10, 2026, 10:41 p.m. |
| PD | Predicate disambiguation | batch_69d96fa55b888190ab1612e93c41aec4 |
completed | April 10, 2026, 9:46 p.m. |
| PDg | Predicate description generation | batch_69d97c7d0598819080cab0a2314bc106 |
completed | April 10, 2026, 10:41 p.m. |
Created at: April 9, 2026, 5:38 p.m.