Triple
T16202581
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Byzantine castle of Arta |
E393239
|
entity |
| Predicate | hasLaterAdditions |
P110135
|
FINISHED |
| Object | Ottoman period fortifications |
—
|
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: Ottoman period fortifications | Statement: [Byzantine castle of Arta, hasLaterAdditions, Ottoman period fortifications]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLaterAdditions Context triple: [Byzantine castle of Arta, hasLaterAdditions, Ottoman period fortifications]
-
A.
laterAdditionsBy
chosen
Indicates that one entity consists of or represents additions or modifications that were made to another entity at a later time.
-
B.
laterIncludedOn
Indicates that one entity was added to, incorporated into, or featured on another entity at a subsequent time.
-
C.
laterEditionContains
Indicates that a later edition of a work includes all or part of the content from an earlier edition.
-
D.
laterModification
Indicates that one entity is a modification or revision that occurs after another in time.
-
E.
hasAdditionalArticlesSince
Indicates that an entity has gained one or more new articles since a specified prior point in time or state.
- 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_69d87f1f5bd08190bd01cac0d5b9d2ef |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e2270b84408190bfbf68f32bfc5b1a |
completed | April 17, 2026, 12:26 p.m. |
| PD | Predicate disambiguation | batch_69e219e11f6081909106b1240a17fd37 |
completed | April 17, 2026, 11:30 a.m. |
Created at: April 10, 2026, 5:03 a.m.