Triple

T21175755
Position Surface form Disambiguated ID Type / Status
Subject Mark Esper E521807 entity
Predicate familyName P18 FINISHED
Object Esper
Esper is a surname most prominently associated with Mark Esper, the former U.S. Secretary of Defense under President Donald Trump.
 E1470704 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: Esper | Statement: [Mark Esper, familyName, Esper]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Esper
Context triple: [Mark Esper, familyName, Esper]
  • A. Esperih
    Esperih is another name for Asparuh of Bulgaria, the 7th-century Bulgar ruler who founded the First Bulgarian Empire in the Balkans.
  • B. Expectane
    Expectane is a fictional fertility drug featured in the comedy film "Junior," used in the experimental male pregnancy undertaken by Dr. Alex Hesse.
  • C. Hesperos
    Hesperos is the ancient Greek personification of the evening star, typically associated with the planet Venus as seen at dusk.
  • D. Hespere
    Hespere is one of the Hesperides, the nymphs of Greek mythology who tended the blissful garden in the far west that contained the golden apples.
  • E. Essa
    Essa is a rural township in Simcoe County, Ontario, Canada, known for its agricultural landscape and proximity to the city of Barrie.
  • 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: Esper
Triple: [Mark Esper, familyName, Esper]
Generated description
Esper is a surname most prominently associated with Mark Esper, the former U.S. Secretary of Defense under President Donald Trump.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Esper
Target entity description: Esper is a surname most prominently associated with Mark Esper, the former U.S. Secretary of Defense under President Donald Trump.
  • A. Esperih
    Esperih is another name for Asparuh of Bulgaria, the 7th-century Bulgar ruler who founded the First Bulgarian Empire in the Balkans.
  • B. Expectane
    Expectane is a fictional fertility drug featured in the comedy film "Junior," used in the experimental male pregnancy undertaken by Dr. Alex Hesse.
  • C. Hesperos
    Hesperos is the ancient Greek personification of the evening star, typically associated with the planet Venus as seen at dusk.
  • D. Hespere
    Hespere is one of the Hesperides, the nymphs of Greek mythology who tended the blissful garden in the far west that contained the golden apples.
  • E. Essa
    Essa is a rural township in Simcoe County, Ontario, Canada, known for its agricultural landscape and proximity to the city of Barrie.
  • 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_69e0b50e30748190b186824a206d39b9 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7271597288190b04baff9ca8d866c completed April 21, 2026, 7:28 a.m.
NED1 Entity disambiguation (via context triple) batch_6a09757772b88190b7eab700ab116596 completed May 17, 2026, 7:59 a.m.
NEDg Description generation batch_6a09775849588190a7d28b0bb6912a01 completed May 17, 2026, 8:07 a.m.
NED2 Entity disambiguation (via description) batch_6a097878a6248190a3573b84aaa29827 completed May 17, 2026, 8:12 a.m.
Created at: April 16, 2026, 3 p.m.