Triple
T18938592
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Viroconium Cornoviorum |
E463319
|
entity |
| Predicate | OldWorkInstanceOf |
P23899
|
FINISHED |
| Object | surviving fragment of basilica wall |
—
|
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: surviving fragment of basilica wall | Statement: [Viroconium Cornoviorum, OldWorkInstanceOf, surviving fragment of basilica wall]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: OldWorkInstanceOf Context triple: [Viroconium Cornoviorum, OldWorkInstanceOf, surviving fragment of basilica wall]
-
A.
sourceWorkInstanceOf
Indicates that a source work is an instance or specific realization of a more general work or abstract creative concept.
-
B.
sonInstanceOf
Indicates that an entity is a specific instance or example of the general concept or class represented by "son."
-
C.
instanceOf
relation of type constraints
-
D.
originalWorkInstanceOf
Indicates that an original work is a specific instance or realization of a more general work, type, or conceptual creation.
-
E.
previousInstanceOf
chosen
Indicates that one entity is an earlier occurrence or version of another entity in a sequence or history.
- 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_69d8dcfec90481909e926be9767e5779 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d3ea39dc8190a2f773e09e11e6d1 |
completed | April 20, 2026, 7:21 a.m. |
| PD | Predicate disambiguation | batch_69e4a2efec5c8190840704016bf547a1 |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, 11:59 a.m.