Triple
T29056155
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Princess of Colchis |
E735389
|
entity |
| Predicate | notableAncientSource |
P157970
|
FINISHED |
| Object | Apollonius of Rhodes |
E206090
|
NE 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: Apollonius of Rhodes | Statement: [Princess of Colchis, notableAncientSource, Apollonius of Rhodes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableAncientSource Context triple: [Princess of Colchis, notableAncientSource, Apollonius of Rhodes]
-
A.
knownByAncientCivilization
Indicates that something was recognized, documented, or understood by an ancient civilization.
-
B.
linkedToAncientSource
Indicates that one entity is connected or traceable to an ancient source, origin, or reference.
-
C.
discoveredInAntiquity
Indicates that something was found, identified, or recognized during ancient historical times rather than in the modern era.
-
D.
namedInHistoricalSources
Indicates that an entity is explicitly mentioned or identified in historical documents or records.
-
E.
ancientAttributionBy
chosen
Indicates that an entity is credited or assigned to another entity based on ancient or historical sources rather than modern evidence.
- F. None of above.
Provenance (4 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_69f077e64b88819094d37bdbca8191b3 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_6a021f84715881908e25b6548e7cf62e |
completed | May 11, 2026, 6:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a251f7bc5988190b8f64ef8a28777e6 |
completed | June 7, 2026, 7:36 a.m. |
| PD | Predicate disambiguation | batch_6a021739b7288190a4ca94c04074c78a |
completed | May 11, 2026, 5:51 p.m. |
Created at: April 28, 2026, 10:11 a.m.