Triple
T28474455
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Classis Britannica |
E720523
|
entity |
| Predicate | insigniaFoundOn |
P97951
|
FINISHED |
| Object | tiles in Britain |
—
|
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: tiles in Britain | Statement: [Classis Britannica, insigniaFoundOn, tiles in Britain]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: insigniaFoundOn Context triple: [Classis Britannica, insigniaFoundOn, tiles in Britain]
-
A.
insigniaLocation
chosen
Indicates the physical position or placement of an insignia on or relative to an entity.
-
B.
insigniaUsedFor
Indicates that a particular insignia is employed or designated for a specific purpose, function, or use.
-
C.
insigniaName
Indicates the specific name or designation assigned to an insignia associated with an entity.
-
D.
hasInsigniaComponent
Indicates that an entity includes, bears, or is composed of a particular insignia or emblem as one of its components.
-
E.
insigniaCaption
Indicates the text that serves as a caption or explanatory label specifically for an insignia.
- 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_69f01a5983f48190b7c1b8857245a4f7 |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f64ee43528819094df428388d46bdd |
completed | May 2, 2026, 7:22 p.m. |
| PD | Predicate disambiguation | batch_69f64caede108190a35cc7cbfead866f |
completed | May 2, 2026, 7:12 p.m. |
Created at: April 28, 2026, 2:51 a.m.