Triple

T2856289
Position Surface form Disambiguated ID Type / Status
Subject Facebook (Meta) headquarters E63207 entity
Predicate hasBuilding P105 FINISHED
Object MPK20
MPK20 is a major office building on Meta’s Menlo Park campus, known for its expansive, park-like rooftop and open-plan workspace designed to house thousands of employees.
 E305000 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: MPK20 | Statement: [Facebook (Meta) headquarters, hasBuilding, MPK20]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: MPK20
Context triple: [Facebook (Meta) headquarters, hasBuilding, MPK20]
  • A. MK 2
    MK 2 is the small natural satellite orbiting the distant dwarf planet Makemake in the Kuiper Belt.
  • B. MK
    MK is the commonly used abbreviation for Umkhonto we Sizwe, the former armed wing of South Africa’s African National Congress during the anti-apartheid struggle.
  • C. MK
    MK is the two-letter ISO 3166-1 alpha-2 country code assigned to North Macedonia.
  • D. Mk2
    The Mk2 is the second generation of the Volkswagen Golf, a popular compact car produced in the 1980s and early 1990s known for its improved refinement, safety, and performance over its predecessor.
  • E. KMK
    KMK is the central coordinating body of Germany’s state education and cultural ministers, responsible for harmonizing policies across the federal states.
  • 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: MPK20
Triple: [Facebook (Meta) headquarters, hasBuilding, MPK20]
Generated description
MPK20 is a major office building on Meta’s Menlo Park campus, known for its expansive, park-like rooftop and open-plan workspace designed to house thousands of employees.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: MPK20
Target entity description: MPK20 is a major office building on Meta’s Menlo Park campus, known for its expansive, park-like rooftop and open-plan workspace designed to house thousands of employees.
  • A. MK 2
    MK 2 is the small natural satellite orbiting the distant dwarf planet Makemake in the Kuiper Belt.
  • B. MK
    MK is the commonly used abbreviation for Umkhonto we Sizwe, the former armed wing of South Africa’s African National Congress during the anti-apartheid struggle.
  • C. MK
    MK is the two-letter ISO 3166-1 alpha-2 country code assigned to North Macedonia.
  • D. Mk2
    The Mk2 is the second generation of the Volkswagen Golf, a popular compact car produced in the 1980s and early 1990s known for its improved refinement, safety, and performance over its predecessor.
  • E. KMK
    KMK is the central coordinating body of Germany’s state education and cultural ministers, responsible for harmonizing policies across the federal states.
  • 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_69ab4c41e8c08190a9e8f5249cc12610 completed March 6, 2026, 9:50 p.m.
NER Named-entity recognition batch_69abdf62308081908a65decdd5d6f918 completed March 7, 2026, 8:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69b01d8d0eec8190b0b29407264fb2bd completed March 10, 2026, 1:33 p.m.
NEDg Description generation batch_69b020869d7c81909d9a00cc43f0ed7d completed March 10, 2026, 1:45 p.m.
NED2 Entity disambiguation (via description) batch_69b02122270c8190a063f09acefcbb18 completed March 10, 2026, 1:48 p.m.
Created at: March 6, 2026, 10:02 p.m.