Triple
T26422612
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman walls of Eboracum |
E664279
|
entity |
| Predicate | partlyOverlainBy |
P16474
|
FINISHED |
| Object | medieval York city walls |
—
|
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: medieval York city walls | Statement: [Roman walls of Eboracum, partlyOverlainBy, medieval York city walls]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partlyOverlainBy Context triple: [Roman walls of Eboracum, partlyOverlainBy, medieval York city walls]
-
A.
partlyCoveredBy
chosen
Indicates that one entity is covered or overlapped by another entity, but only to a partial extent rather than completely.
-
B.
overlies
Indicates that one entity is positioned directly above and covering or resting on another entity, often with partial or complete contact.
-
C.
overriddenInPartBy
Indicates that one item’s provisions or effects are partially superseded or modified by another item.
-
D.
partlyConsistsOf
Indicates that one entity is composed in part, but not entirely, of another entity.
-
E.
partiallyEnclosed
Indicates that one entity surrounds or covers another entity to some extent, but not completely.
- 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_69ee883a04ec81908883c4559f8c7e24 |
completed | April 26, 2026, 9:48 p.m. |
| NER | Named-entity recognition | batch_69f61f12b0f08190bc4a16907941864c |
completed | May 2, 2026, 3:58 p.m. |
| PD | Predicate disambiguation | batch_69f61b3a8ae0819090189fbd8eb19f2f |
completed | May 2, 2026, 3:41 p.m. |
Created at: April 26, 2026, 11:44 p.m.