Triple

T11472275
Position Surface form Disambiguated ID Type / Status
Subject Investigation Discovery E271937 entity
Predicate shortName P43 FINISHED
Object ID
ID is an American true crime–focused television network known for its documentaries and docudramas about real criminal cases and investigations.
 E927360 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: ID | Statement: [Investigation Discovery, shortName, ID]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ID
Context triple: [Investigation Discovery, shortName, ID]
  • A. ID
    ID is the two-letter United States Postal Service abbreviation for the state of Idaho.
  • B. ID
    ID is the ISO 3166-1 alpha-2 country code for Indonesia, a Southeast Asian nation made up of thousands of islands.
  • C. UID
    UID is a scholarly work that examines the variety and functioning of institutions within economic and social systems.
  • D. Uid
    Uid is a Symfony component that provides tools for generating and working with unique identifiers such as UUIDs and ULIDs in PHP applications.
  • E. OID
    OID is Oracle Internet Directory, an LDAP-compliant directory service that stores and manages user and application identity information within Oracle environments.
  • 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: ID
Triple: [Investigation Discovery, shortName, ID]
Generated description
ID is an American true crime–focused television network known for its documentaries and docudramas about real criminal cases and investigations.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ID
Target entity description: ID is an American true crime–focused television network known for its documentaries and docudramas about real criminal cases and investigations.
  • A. ID
    ID is the two-letter United States Postal Service abbreviation for the state of Idaho.
  • B. ID
    ID is the ISO 3166-1 alpha-2 country code for Indonesia, a Southeast Asian nation made up of thousands of islands.
  • C. UID
    UID is a scholarly work that examines the variety and functioning of institutions within economic and social systems.
  • D. Uid
    Uid is a Symfony component that provides tools for generating and working with unique identifiers such as UUIDs and ULIDs in PHP applications.
  • E. OID
    OID is Oracle Internet Directory, an LDAP-compliant directory service that stores and manages user and application identity information within Oracle environments.
  • 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_69d6aae0c8d881908a5a360c0be3242e completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8294b3f388190a587c358313f7260 completed April 9, 2026, 10:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5e95a479c81909a330c9721bd3902 completed April 20, 2026, 8:52 a.m.
NEDg Description generation batch_69e5f15a50b881908d0930021833ae74 completed April 20, 2026, 9:26 a.m.
NED2 Entity disambiguation (via description) batch_69e5f88f16748190826a7fc5d27019d7 completed April 20, 2026, 9:57 a.m.
Created at: April 8, 2026, 9:35 p.m.