Triple

T18198890
Position Surface form Disambiguated ID Type / Status
Subject ESPaDOnS E435729 entity
Predicate associatedSurvey P49793 FINISHED
Object BinaMIcS
BinaMIcS is an astronomical survey project focused on studying magnetism in massive binary star systems.
 E1311770 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: BinaMIcS | Statement: [ESPaDOnS, associatedSurvey, BinaMIcS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: BinaMIcS
Context triple: [ESPaDOnS, associatedSurvey, BinaMIcS]
  • A. MiC
    MiC is the official abbreviation for Italy’s Ministry of Culture, the government body responsible for cultural heritage, arts, and related policies.
  • B. BCI
    BCI is the investigative division of the Virginia State Police responsible for conducting major criminal investigations and supporting law enforcement operations across the state.
  • C. BCI
    BCI is the investigative division of the New York State Police responsible for conducting major criminal investigations and specialized law enforcement operations across the state.
  • D. BCI
    BCI is a Quebec-based interuniversity cooperation bureau that coordinates collaboration and shared initiatives among the province’s universities.
  • E. BCI
    BCI is the statutory body that regulates legal education and the legal profession in India.
  • 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: BinaMIcS
Triple: [ESPaDOnS, associatedSurvey, BinaMIcS]
Generated description
BinaMIcS is an astronomical survey project focused on studying magnetism in massive binary star systems.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: BinaMIcS
Target entity description: BinaMIcS is an astronomical survey project focused on studying magnetism in massive binary star systems.
  • A. MiC
    MiC is the official abbreviation for Italy’s Ministry of Culture, the government body responsible for cultural heritage, arts, and related policies.
  • B. BCI
    BCI is a Quebec-based interuniversity cooperation bureau that coordinates collaboration and shared initiatives among the province’s universities.
  • C. BCI
    BCI is the investigative division of the Virginia State Police responsible for conducting major criminal investigations and supporting law enforcement operations across the state.
  • D. BCI
    BCI is the statutory body that regulates legal education and the legal profession in India.
  • E. BCI
    BCI is the investigative division of the New York State Police responsible for conducting major criminal investigations and specialized law enforcement operations across the state.
  • 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_69d8b90dba6481908e119eb9aa4ca0cb completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4e0d545f4819090285d1446bd3c27 completed April 19, 2026, 2:04 p.m.
NED1 Entity disambiguation (via context triple) batch_6a03980f600c819099f3fb14744f8afa completed May 12, 2026, 9:13 p.m.
NEDg Description generation batch_6a0398fb7fb481908a32c56a798d81fd completed May 12, 2026, 9:17 p.m.
NED2 Entity disambiguation (via description) batch_6a039a2b85888190bbcae1ba9d8ba715 completed May 12, 2026, 9:22 p.m.
Created at: April 10, 2026, 10:31 a.m.