Triple

T36033630
Position Surface form Disambiguated ID Type / Status
Subject Bremsnes Cave E1042334 entity
Predicate hasFindsStoredAt P201428 FINISHED
Object Norwegian museums
Norwegian museums are cultural institutions in Norway that collect, preserve, and exhibit the nation’s historical, artistic, and archaeological heritage.
 E2166921 NE FINISHED

How this triple was built (3 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: Norwegian museums | Statement: [Bremsnes Cave, hasFindsStoredAt, Norwegian museums]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Norwegian museums
Triple: [Bremsnes Cave, hasFindsStoredAt, Norwegian museums]
Generated description
Norwegian museums are cultural institutions in Norway that collect, preserve, and exhibit the nation’s historical, artistic, and archaeological heritage.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: hasFindsStoredAt
Context triple: [Bremsnes Cave, hasFindsStoredAt, Norwegian museums]
  • A. laterStoredIn
    Indicates that an entity is subsequently placed or kept within a particular storage location or container at a later point in time.
  • B. hasFindsDisplayedAt
    Indicates that certain discovered items or finds are being shown or exhibited at a particular location or display context.
  • C. shouldBeStoredAt
    Indicates that an entity is required or recommended to be kept or maintained at a specified location or storage condition.
  • D. laterStoredAt
    Indicates that an entity is stored at a particular location or storage medium at a later point in time relative to some reference event or state.
  • E. storedBy
    Indicates that one entity is kept, maintained, or held in storage by another entity.
  • F. None of above. chosen

Provenance (7 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_69f76e2d7e8c8190bac4e90734566799 completed May 3, 2026, 3:47 p.m.
NER Named-entity recognition batch_69fff4530f908190afe9387f732c2b7e completed May 10, 2026, 2:58 a.m.
NED1 Entity disambiguation (via context triple) batch_6a38cb930a848190bcec41980d2f4d4a completed June 22, 2026, 5:43 a.m.
NEDg Description generation batch_6a38cd0a7b708190afd70d66d8aa7d6d completed June 22, 2026, 5:50 a.m.
NED2 Entity disambiguation (via description) batch_6a38cd8cf4708190a141ec08f61a6087 completed June 22, 2026, 5:52 a.m.
PD Predicate disambiguation batch_69fff3c01a64819091196875b0c88607 completed May 10, 2026, 2:56 a.m.
PDg Predicate description generation batch_69fff4525ce48190b1d760539e68aadc completed May 10, 2026, 2:58 a.m.
Created at: May 3, 2026, 4:07 p.m.