Triple
T20176333
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Derwent church tower |
E492109
|
entity |
| Predicate | hasFunctionFormerly |
P5925
|
FINISHED |
| Object | parish church tower |
—
|
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: parish church tower | Statement: [Derwent church tower, hasFunctionFormerly, parish church tower]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFunctionFormerly Context triple: [Derwent church tower, hasFunctionFormerly, parish church tower]
-
A.
hasFunctionInPresent
Indicates that an entity currently performs, exhibits, or fulfills a specific function or role at the present time.
-
B.
formerFunction
chosen
Indicates that an entity previously held a specific role, position, or function but no longer does so.
-
C.
hasFormerCode
Indicates that an entity was previously identified or referenced by an earlier code that is no longer current.
-
D.
hasFunctionDuring
Indicates that an entity performs or exhibits a specific function only within a specified time period or temporal context.
-
E.
functionedBefore
Indicates that one entity was operational or in working order at an earlier time than another entity.
- 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_69da6266c6888190bc1a3ecf24814d34 |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e668eb50a48190af7de53680ca2f5d |
completed | April 20, 2026, 5:56 p.m. |
| PD | Predicate disambiguation | batch_69e55b0c11cc8190836d1eee5945f000 |
completed | April 19, 2026, 10:45 p.m. |
Created at: April 11, 2026, 11:36 p.m.