Triple

T17106016
Position Surface form Disambiguated ID Type / Status
Subject Laurel, Maryland E415100 entity
Predicate nearInstallation P350 FINISHED
Object Fort Meade E209833 NE FINISHED

How this triple was built (3 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: Fort Meade | Statement: [Laurel, Maryland, nearInstallation, Fort Meade]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fort Meade
Context triple: [Laurel, Maryland, nearInstallation, Fort Meade]
  • A. Fort Meade, Maryland
    Fort Meade, Maryland is a major U.S. Army installation best known as the primary center for American military intelligence and cybersecurity operations.
  • B. Fort Belvoir
    Fort Belvoir is a major United States Army installation in Fairfax County, Virginia, that serves as a key administrative and logistical hub for numerous military and defense agencies.
  • C. Fort McClellan
    Fort McClellan is a former U.S. Army installation near Anniston, Alabama, historically used for infantry, military police, and chemical corps training.
  • D. Fort Dix
    Fort Dix is a major U.S. Army installation in New Jersey that has long served as a key training and mobilization center for American soldiers.
  • E. Fort George G. Meade chosen
    Fort George G. Meade is a major U.S. Army installation in Maryland that serves as a key center for military intelligence, cybersecurity, and defense communications operations.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: nearInstallation
Context triple: [Laurel, Maryland, nearInstallation, Fort Meade]
  • A. nearPass
    Indicates that one entity moves or travels close to another entity without necessarily making direct contact or interaction.
  • B. near chosen
    Indicates that one entity is located at a short distance from another entity in space or position.
  • C. intendedInstallation
    Indicates that one entity is meant or planned to be installed in, on, or as part of another entity or environment.
  • D. associatedInstallation
    Indicates a relationship where one entity is linked to, or occurs in connection with, a particular installation (such as a facility, system, or setup) with which it is contextually or functionally related.
  • E. typeOfInstallation
    Indicates the specific kind or category of installation associated with an entity (e.g., how or in what form something is installed).
  • F. None of above.

Provenance (4 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_69d886cfc8e88190b05ba466edd35591 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3dc2750b481908de18e8cb8f2195c completed April 18, 2026, 7:31 p.m.
NED1 Entity disambiguation (via context triple) batch_6a013a019540819083ce6100b24f8cfb completed May 11, 2026, 2:08 a.m.
PD Predicate disambiguation batch_69e35d6b1b988190a8d6b6fe78c35e59 completed April 18, 2026, 10:31 a.m.
Created at: April 10, 2026, 5:35 a.m.