Triple

T37168818
Position Surface form Disambiguated ID Type / Status
Subject Erawan Shrine E920856 entity
Predicate hasTypeOfOffering P34857 FINISHED
Object marigold garlands 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: marigold garlands | Statement: [Erawan Shrine, hasTypeOfOffering, marigold garlands]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasTypeOfOffering
Context triple: [Erawan Shrine, hasTypeOfOffering, marigold garlands]
  • A. hasOffering
    Indicates that one entity provides, presents, or makes available an offering (such as a product, service, or item) to another entity or context.
  • B. offeringType chosen
    Indicates the category or nature of what is being offered in a transaction or interaction (e.g., product, service, or other type of offering).
  • C. isOfferedBy
    Indicates that a service, product, or opportunity is provided or made available by a particular entity.
  • D. providesOfferingsTo
    Indicates that one entity supplies or presents offerings, such as goods, services, or benefits, to another entity.
  • E. usesOffering
    Indicates that one entity makes use of, applies, or relies on a particular offering provided by another entity.
  • 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_69f76ea16f288190b445aa1604d996f4 completed May 3, 2026, 3:49 p.m.
NER Named-entity recognition batch_69ffc516d1908190b475f5a6156b0ca8 completed May 9, 2026, 11:36 p.m.
PD Predicate disambiguation batch_69ffc4a946e08190b3535a5dc15ac484 completed May 9, 2026, 11:35 p.m.
Created at: May 3, 2026, 4:15 p.m.