Triple
T8192449
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Verulamium |
E191343
|
entity |
| Predicate | hasVisibleRemains |
P35040
|
FINISHED |
| Object | Roman theatre |
—
|
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: Roman theatre | Statement: [Verulamium, hasVisibleRemains, Roman theatre]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasVisibleRemains Context triple: [Verulamium, hasVisibleRemains, Roman theatre]
-
A.
hasRemainsOf
Indicates that one entity physically contains, preserves, or is associated with the leftover physical traces or remnants of another entity.
-
B.
visibleRemains
chosen
Indicates that some physical remnants of an entity or event can still be seen or visually detected.
-
C.
hasVisibility
Indicates that one entity can perceive, view, or access another entity or its information under certain conditions.
-
D.
isVisibleAs
Indicates that one entity can be perceived or appears to observers under the form, name, or representation of another entity.
-
E.
visibleAt
Indicates that one entity can be seen or perceived from a specific location, viewpoint, or context at a given time.
- 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_69ca82c5b6948190a583c096fb0a6c71 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb5c1d7aa48190adbbce88b3bed1a3 |
completed | March 31, 2026, 5:31 a.m. |
| PD | Predicate disambiguation | batch_69cb36aac86081909b83636e352e0ced |
completed | March 31, 2026, 2:51 a.m. |
Created at: March 30, 2026, 5:42 p.m.