Triple
T30984604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St Peter’s Church, Barton-upon-Humber |
E789485
|
entity |
| Predicate | underwentExcavation |
P33350
|
FINISHED |
| Object | 1970s |
—
|
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: 1970s | Statement: [St Peter’s Church, Barton-upon-Humber, underwentExcavation, 1970s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: underwentExcavation Context triple: [St Peter’s Church, Barton-upon-Humber, underwentExcavation, 1970s]
-
A.
excavatedAs
Indicates that one entity has been dug out, uncovered, or removed from its surrounding material or context in the form or role of another specified entity.
-
B.
excavatedUnder
Indicates that one entity was dug out, uncovered, or removed from beneath another entity during an excavation process.
-
C.
excavatedAfter
Indicates that one excavation event occurred later in time than another excavation event.
-
D.
excavatedFor
Indicates that something has been dug out or uncovered from the ground specifically for the benefit, use, or purpose of another entity.
-
E.
excavated
chosen
Indicates that one entity has dug out, uncovered, or removed earth or material from another entity, typically to reveal or extract what lies beneath.
- 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_69f224c550b081909ddfceb0c3d03bdd |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fb2e940d5c8190bceae77daf4ef512 |
completed | May 6, 2026, 12:05 p.m. |
| PD | Predicate disambiguation | batch_69f9fec70bd881909c658a3c5020318b |
completed | May 5, 2026, 2:29 p.m. |
Created at: April 29, 2026, 8:56 p.m.