Triple

T7157007
Position Surface form Disambiguated ID Type / Status
Subject Exicure, Inc. E166837 entity
Predicate hasCollaborationWith P398 FINISHED
Object Ipsen
Ipsen is a global biopharmaceutical company headquartered in France, focused on specialty care areas such as oncology, neuroscience, and rare diseases.
 E645749 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: Ipsen | Statement: [Exicure, Inc., hasCollaborationWith, Ipsen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ipsen
Context triple: [Exicure, Inc., hasCollaborationWith, Ipsen]
  • A. Roche
    Roche is a major Swiss multinational healthcare company and one of the world’s leading pharmaceutical and diagnostics firms.
  • B. Roche
    Roche is a common surname of French origin borne by various notable individuals across fields such as architecture, politics, and the arts.
  • C. Novartis
    Novartis is a global Swiss-based pharmaceutical company known for developing innovative medicines across a wide range of therapeutic areas.
  • D. Arthus-Bertrand
    Arthus-Bertrand is the hyphenated French family name of photographer and environmentalist Yann Arthus-Bertrand, known for his aerial imagery and ecological advocacy.
  • E. Sandoz
    Sandoz is a historic Swiss pharmaceutical company best known as a predecessor of Novartis and a major player in generic medicines.
  • 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: Ipsen
Triple: [Exicure, Inc., hasCollaborationWith, Ipsen]
Generated description
Ipsen is a global biopharmaceutical company headquartered in France, focused on specialty care areas such as oncology, neuroscience, and rare diseases.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ipsen
Target entity description: Ipsen is a global biopharmaceutical company headquartered in France, focused on specialty care areas such as oncology, neuroscience, and rare diseases.
  • A. Roche
    Roche is a major Swiss multinational healthcare company and one of the world’s leading pharmaceutical and diagnostics firms.
  • B. Roche
    Roche is a common surname of French origin borne by various notable individuals across fields such as architecture, politics, and the arts.
  • C. Novartis
    Novartis is a global Swiss-based pharmaceutical company known for developing innovative medicines across a wide range of therapeutic areas.
  • D. Arthus-Bertrand
    Arthus-Bertrand is the hyphenated French family name of photographer and environmentalist Yann Arthus-Bertrand, known for his aerial imagery and ecological advocacy.
  • E. Sandoz
    Sandoz is a historic Swiss pharmaceutical company best known as a predecessor of Novartis and a major player in generic medicines.
  • 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_69c68887a5cc8190bec0ea96227164f7 completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6e80f14808190907ee84523630d85 completed March 27, 2026, 8:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7adb530388190b68fa05418d3e184 completed March 28, 2026, 10:30 a.m.
NEDg Description generation batch_69c7ae830c74819091d6d65ac6fba32b completed March 28, 2026, 10:33 a.m.
NED2 Entity disambiguation (via description) batch_69c7af1133b08190a32dccf82015c19e completed March 28, 2026, 10:36 a.m.
Created at: March 27, 2026, 2:47 p.m.