Triple

T19952995
Position Surface form Disambiguated ID Type / Status
Subject Lily E479604 entity
Predicate associatedWithCharacter P1481 FINISHED
Object Rosemary NE NERFINISHED

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: Rosemary | Statement: [Lily, associatedWithCharacter, Rosemary]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rosemary
Context triple: [Lily, associatedWithCharacter, Rosemary]
  • A. Rosemary chosen
    Rosemary is a feminine given name of Latin origin, commonly associated with the aromatic herb and often used in English-speaking countries.
  • B. Salvia officinalis
    Salvia officinalis is a perennial aromatic herb, commonly known as common sage, widely used as a culinary seasoning and traditional medicinal plant.
  • C. Laurus nobilis
    Laurus nobilis is an aromatic evergreen tree native to the Mediterranean region, best known as the culinary bay laurel whose leaves are widely used as a herb in cooking.
  • D. Pepperminta
    Pepperminta is an experimental feature film by Swiss visual artist Pipilotti Rist that blends surreal imagery, vivid color, and playful feminist themes in a dreamlike narrative.
  • E. Lovage
    Lovage is a downtempo/trip-hop musical project known for its sultry, cinematic sound and collaboration between artists including Mike Patton and Dan the Automator.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e522a17c819095165d4d24939fd8 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65aee23488190bd92c1593fbc241c completed April 20, 2026, 4:57 p.m.
Created at: April 10, 2026, 1:54 p.m.