Triple

T8296548
Position Surface form Disambiguated ID Type / Status
Subject Rosemary Harris E194233 entity
Predicate givenName P17 FINISHED
Object Rosemary E113312 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: Rosemary | Statement: [Rosemary Harris, givenName, Rosemary]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rosemary
Context triple: [Rosemary Harris, givenName, 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. Ruta graveolens
    Ruta graveolens, commonly known as rue, is a strongly aromatic perennial herb traditionally used in medicine, cooking, and as an ornamental plant.
  • E. Lavandula
    Lavandula is a genus of aromatic flowering plants commonly known as lavender, widely cultivated for its fragrant oils, ornamental value, and use in culinary and medicinal applications.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69ca82e50ebc81909aa7b260c76bd757 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb7df887148190bddc2609bc885cb4 completed March 31, 2026, 7:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd68ad2f248190a1de95c01ddee259 completed April 1, 2026, 6:49 p.m.
Created at: March 30, 2026, 5:53 p.m.