Triple

T22740860
Position Surface form Disambiguated ID Type / Status
Subject Haderslev Municipality E562407 entity
Predicate contains P35 FINISHED
Object Gram
Gram is a small town in southern Denmark known for its historic castle and rich fossil deposits.
 E1551947 NE FINISHED

How this triple was built (4 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: Gram | Statement: [Haderslev Municipality, contains, Gram]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gram
Context triple: [Haderslev Municipality, contains, Gram]
  • A. Gram
    Gram is a legendary sword from Norse mythology, famously wielded by the hero Sigurd to slay the dragon Fafnir.
  • B. Gram
    Gram is a surname of Scandinavian origin borne by various notable individuals, including Norwegian politician Bjørn Arild Gram.
  • C. Kilo
    Kilo is a hip-hop track by Clipse known for its vivid, metaphor-laden depictions of cocaine dealing.
  • D. Kilo
    Kilo is a residential district in the city of Espoo, Finland, known for its apartment blocks, local services, and good commuter rail connections to Helsinki and surrounding areas.
  • E. Gramos
    Gramos is a mountain massif on the border between Greece and Albania, known for its rugged terrain and natural beauty within the Pindus mountain range.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Gram
Triple: [Haderslev Municipality, contains, Gram]
Generated description
Gram is a small town in southern Denmark known for its historic castle and rich fossil deposits.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Gram
Target entity description: Gram is a small town in southern Denmark known for its historic castle and rich fossil deposits.
  • A. Gram
    Gram is a surname of Scandinavian origin borne by various notable individuals, including Norwegian politician Bjørn Arild Gram.
  • B. Gram
    Gram is a legendary sword from Norse mythology, famously wielded by the hero Sigurd to slay the dragon Fafnir.
  • C. Kilo
    Kilo is a hip-hop track by Clipse known for its vivid, metaphor-laden depictions of cocaine dealing.
  • D. Kilo
    Kilo is a residential district in the city of Espoo, Finland, known for its apartment blocks, local services, and good commuter rail connections to Helsinki and surrounding areas.
  • E. Gramos
    Gramos is a mountain massif on the border between Greece and Albania, known for its rugged terrain and natural beauty within the Pindus mountain range.
  • F. None of above. chosen

Provenance (5 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_69e245513a5c81908d5cb471b4fc429d completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17972fde8819086094cea289a2af8 completed April 29, 2026, 3:22 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b8fd07e9481909ff8057024ea2d94 completed May 18, 2026, 10:16 p.m.
NEDg Description generation batch_6a0b92e5412c81909968a22571229283 completed May 18, 2026, 10:29 p.m.
NED2 Entity disambiguation (via description) batch_6a0b93668f0c8190b86094e42fa89c1d completed May 18, 2026, 10:32 p.m.
Created at: April 17, 2026, 3:23 p.m.