Triple

T17557418
Position Surface form Disambiguated ID Type / Status
Subject HAL (Hypertext Application Language) E427622 entity
Predicate abbreviation P43 FINISHED
Object HAL
HAL (Hypertext Application Language) is a simple, JSON- and XML-based format for representing hypermedia resources and links in RESTful APIs.
 E1275197 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: HAL | Statement: [HAL (Hypertext Application Language), abbreviation, HAL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: HAL
Context triple: [HAL (Hypertext Application Language), abbreviation, HAL]
  • A. HAL
    HAL is the ICAO airline designator used to identify Hawaiian Airlines in international aviation operations.
  • B. HAL
    HAL is the stock ticker symbol for Halliburton Company, a major American oilfield services and energy industry equipment provider.
  • C. HAL
    HAL is the vehicle registration code used on license plates for the German city of Halle (Saale).
  • D. HAL
    HAL is an open-access multidisciplinary archive and repository for scholarly documents, widely used by researchers to share and preserve their scientific publications.
  • E. HAL
    HAL is the National Rail station code for Hale railway station in Greater Manchester, England.
  • 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: HAL
Triple: [HAL (Hypertext Application Language), abbreviation, HAL]
Generated description
HAL (Hypertext Application Language) is a simple, JSON- and XML-based format for representing hypermedia resources and links in RESTful APIs.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: HAL
Target entity description: HAL (Hypertext Application Language) is a simple, JSON- and XML-based format for representing hypermedia resources and links in RESTful APIs.
  • A. HAL
    HAL is an open-access multidisciplinary archive and repository for scholarly documents, widely used by researchers to share and preserve their scientific publications.
  • B. HAL
    HAL is the vehicle registration code used on license plates for the German city of Halle (Saale).
  • C. HAL
    HAL is the stock ticker symbol for Halliburton Company, a major American oilfield services and energy industry equipment provider.
  • D. HAL
    HAL is the ICAO airline designator used to identify Hawaiian Airlines in international aviation operations.
  • E. HAL
    HAL is the National Rail station code for Hale railway station in Greater Manchester, England.
  • 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_69d889df6dc081908f67dbadc03c07ee completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e4562413d08190acaa5272046d3626 completed April 19, 2026, 4:12 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01d2948ae0819083b90516b11d2485 completed May 11, 2026, 12:59 p.m.
NEDg Description generation batch_6a01d43430d481909b07d8ecc09a185f completed May 11, 2026, 1:05 p.m.
NED2 Entity disambiguation (via description) batch_6a01d4c609fc819089147744317d4be3 completed May 11, 2026, 1:08 p.m.
Created at: April 10, 2026, 5:50 a.m.