Triple
T24606183
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Colston Bassett |
E608977
|
entity |
| Predicate | hasOldChurch |
P15000
|
FINISHED |
| Object | ruined church of St Mary |
—
|
NE NERFINISHED |
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: ruined church of St Mary | Statement: [Colston Bassett, hasOldChurch, ruined church of St Mary]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOldChurch Context triple: [Colston Bassett, hasOldChurch, ruined church of St Mary]
-
A.
hasChurch
chosen
Indicates that a place or entity possesses, contains, or is associated with a church.
-
B.
hadNationalChurch
Indicates that a country or region recognized a particular church as its official or primary national religious institution.
-
C.
hasAncientChristianHeritage
Indicates that an entity possesses a historical connection to early or longstanding Christian traditions, communities, or influences.
-
D.
earlierChurchUsedBy
Indicates that one church building was used by a group or congregation before they used another, later church building.
-
E.
hasChurchmanship
Indicates that an entity adheres to or is associated with a particular style, tradition, or practice within a Christian church.
- 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_69e2c4d060e08190ac9f7c49b1036e20 |
completed | April 17, 2026, 11:40 p.m. |
| NER | Named-entity recognition | batch_69f2be044d4c819094e14eda28d371a7 |
completed | April 30, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f2a6ca751c8190a040c10d701ecf3a |
completed | April 30, 2026, 12:48 a.m. |
Created at: April 18, 2026, 2:31 a.m.