Triple

T1753303
Position Surface form Disambiguated ID Type / Status
Subject Marvin Bush E38495 entity
Predicate employer P7 FINISHED
Object Stratesec
Stratesec was a U.S.-based security company known for providing aviation and facility security services, including contracts at high-profile sites in the late 1990s and early 2000s.
 E196638 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: Stratesec | Statement: [Marvin Bush, employer, Stratesec]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Stratesec
Context triple: [Marvin Bush, employer, Stratesec]
  • A. Ornex
    Ornex is a small commune in the Ain department of eastern France, located near the Swiss border in the Pays de Gex region.
  • B. Volacom
    Volacom is a company founded by Tesla co-founder and battery technology pioneer JB Straubel, likely focused on advanced engineering and sustainable technology solutions.
  • C. Setonix
    Setonix is a genus of small marsupials best known for including the quokka, a short-tailed wallaby native to southwestern Australia.
  • D. Zenta
    Zenta is a historic town in northern Serbia, best known as the site of a decisive 1697 battle between the Habsburg Monarchy and the Ottoman Empire.
  • E. Elxsi
    Elxsi was a computer company known for developing high-performance minicomputers and multiprocessor systems in the late 20th century.
  • 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: Stratesec
Triple: [Marvin Bush, employer, Stratesec]
Generated description
Stratesec was a U.S.-based security company known for providing aviation and facility security services, including contracts at high-profile sites in the late 1990s and early 2000s.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Stratesec
Target entity description: Stratesec was a U.S.-based security company known for providing aviation and facility security services, including contracts at high-profile sites in the late 1990s and early 2000s.
  • A. Ornex
    Ornex is a small commune in the Ain department of eastern France, located near the Swiss border in the Pays de Gex region.
  • B. Volacom
    Volacom is a company founded by Tesla co-founder and battery technology pioneer JB Straubel, likely focused on advanced engineering and sustainable technology solutions.
  • C. Setonix
    Setonix is a genus of small marsupials best known for including the quokka, a short-tailed wallaby native to southwestern Australia.
  • D. Zenta
    Zenta is a historic town in northern Serbia, best known as the site of a decisive 1697 battle between the Habsburg Monarchy and the Ottoman Empire.
  • E. Elxsi
    Elxsi was a computer company known for developing high-performance minicomputers and multiprocessor systems in the late 20th century.
  • 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_69a8862bdb2081908aefe831c8aa8017 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa64169c508190a33074fb06e9c755 completed March 6, 2026, 5:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69ada0e625c48190a0fbda31010bdc5f completed March 8, 2026, 4:16 p.m.
NEDg Description generation batch_69ada1e3587c8190bca329c68ff31c41 completed March 8, 2026, 4:20 p.m.
NED2 Entity disambiguation (via description) batch_69ada2977bfc8190ad028e17184fccaa completed March 8, 2026, 4:23 p.m.
Created at: March 4, 2026, 7:31 p.m.