Triple

T4221594
Position Surface form Disambiguated ID Type / Status
Subject Cambridge life sciences ecosystem E94351 entity
Predicate hasKeyCompany P51457 FINISHED
Object Domantis
Domantis is a biotechnology company based in the Cambridge life sciences cluster, known for developing next-generation antibody-based therapeutics.
 E422487 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: Domantis | Statement: [Cambridge life sciences ecosystem, hasKeyCompany, Domantis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Domantis
Context triple: [Cambridge life sciences ecosystem, hasKeyCompany, Domantis]
  • A. Evander
    Evander is a masculine given name most famously borne by American former heavyweight boxing champion Evander Holyfield.
  • B. Kalisto
    Kalisto is a high-flying Mexican-American professional wrestler best known for his acrobatic lucha libre style in WWE.
  • C. Adamantas
    Adamantas is the main port town and primary tourist hub of the Greek island of Milos in the Aegean Sea.
  • D. Victorino
    Victorino is a masculine given name, primarily used in Spanish and Portuguese-speaking cultures, derived from the name Victor.
  • E. Herculez Gomez
    Herculez Gomez is a retired American soccer forward known for his goal-scoring in Major League Soccer and appearances with the United States national team.
  • 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: Domantis
Triple: [Cambridge life sciences ecosystem, hasKeyCompany, Domantis]
Generated description
Domantis is a biotechnology company based in the Cambridge life sciences cluster, known for developing next-generation antibody-based therapeutics.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Domantis
Target entity description: Domantis is a biotechnology company based in the Cambridge life sciences cluster, known for developing next-generation antibody-based therapeutics.
  • A. Evander
    Evander is a masculine given name most famously borne by American former heavyweight boxing champion Evander Holyfield.
  • B. Kalisto
    Kalisto is a high-flying Mexican-American professional wrestler best known for his acrobatic lucha libre style in WWE.
  • C. Adamantas
    Adamantas is the main port town and primary tourist hub of the Greek island of Milos in the Aegean Sea.
  • D. Victorino
    Victorino is a masculine given name, primarily used in Spanish and Portuguese-speaking cultures, derived from the name Victor.
  • E. Herculez Gomez
    Herculez Gomez is a retired American soccer forward known for his goal-scoring in Major League Soccer and appearances with the United States national team.
  • 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_69b3451997e08190851db4a9a588837d completed March 12, 2026, 10:58 p.m.
NER Named-entity recognition batch_69b34f7d20b48190a404638c68c31026 completed March 12, 2026, 11:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69b59642720c81908e68a56b3d30eef9 completed March 14, 2026, 5:09 p.m.
NEDg Description generation batch_69b596cb73ac81909f83daca406ad8c4 completed March 14, 2026, 5:11 p.m.
NED2 Entity disambiguation (via description) batch_69b59a9c386081909c21ad554d403bfc completed March 14, 2026, 5:27 p.m.
Created at: March 12, 2026, 11:04 p.m.