Triple
T16246896
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bridge of Arta |
E394393
|
entity |
| Predicate | hasLegendCharacter |
P111069
|
FINISHED |
| Object | master builder’s wife |
—
|
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: master builder’s wife | Statement: [Bridge of Arta, hasLegendCharacter, master builder’s wife]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLegendCharacter Context triple: [Bridge of Arta, hasLegendCharacter, master builder’s wife]
-
A.
hasLegendAssociatedWith
Indicates that something is connected to or accompanied by a traditional story, myth, or legend.
-
B.
hasIconicCharacter
Indicates that something is associated with a character widely recognized as emblematic or highly representative of it.
-
C.
hasCharacters
chosen
Indicates that an entity (such as a work or story) includes or features certain characters as part of its content.
-
D.
hasHistoricalLegend
Indicates that there exists a traditional story, myth, or legend associated with the subject, typically rooted in historical or cultural narratives.
-
E.
hasMediaLegend
Indicates that an entity is associated with a media-specific legend or caption that explains or describes that media.
- 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_69d87f2171208190951025e526947816 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e245931074819096f38003da70f271 |
completed | April 17, 2026, 2:37 p.m. |
| PD | Predicate disambiguation | batch_69e219ee6f6481909663b388dc99770a |
completed | April 17, 2026, 11:30 a.m. |
Created at: April 10, 2026, 5:04 a.m.