Triple
T973947
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New York City Department of Correction |
E21006
|
entity |
| Predicate | shortName |
P43
|
FINISHED |
| Object |
DOC
DOC is the commonly used abbreviation for the New York City Department of Correction, the agency responsible for operating the city’s jail system.
|
E115322
|
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: DOC | Statement: [New York City Department of Correction, shortName, DOC]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: DOC Context triple: [New York City Department of Correction, shortName, DOC]
-
A.
DOC
DOC is the commonly used abbreviation for the Division of Organic Chemistry, a professional organization focused on advancing research and education in organic chemistry.
-
B.
ReDoc
ReDoc is an open-source tool that generates interactive, user-friendly API documentation from OpenAPI (Swagger) specifications.
-
C.
DO
DO is the two-letter ISO 3166-1 alpha-2 country code assigned to the Dominican Republic.
-
D.
Doc
Doc is the widely used nickname of Glenn "Doc" Rivers, a former NBA player and championship-winning head coach.
-
E.
docuverse
Docuverse is Ted Nelson’s visionary concept of a universal, interconnected digital library where all documents are permanently linked and traceable across a global hypertext system.
- 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: DOC Triple: [New York City Department of Correction, shortName, DOC]
Generated description
DOC is the commonly used abbreviation for the New York City Department of Correction, the agency responsible for operating the city’s jail system.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: DOC Target entity description: DOC is the commonly used abbreviation for the New York City Department of Correction, the agency responsible for operating the city’s jail system.
-
A.
DOC
DOC is the commonly used abbreviation for the Division of Organic Chemistry, a professional organization focused on advancing research and education in organic chemistry.
-
B.
ReDoc
ReDoc is an open-source tool that generates interactive, user-friendly API documentation from OpenAPI (Swagger) specifications.
-
C.
DO
DO is the two-letter ISO 3166-1 alpha-2 country code assigned to the Dominican Republic.
-
D.
Doc
Doc is the widely used nickname of Glenn "Doc" Rivers, a former NBA player and championship-winning head coach.
-
E.
docuverse
Docuverse is Ted Nelson’s visionary concept of a universal, interconnected digital library where all documents are permanently linked and traceable across a global hypertext system.
- 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_69a493c2b62c8190b616351789ec47f8 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b45f28f081908d41b2d7f353708d |
completed | March 1, 2026, 9:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac170a00f481909da0394531ac24fe |
completed | March 7, 2026, 12:16 p.m. |
| NEDg | Description generation | batch_69ac18e9be2081909770ab2ead56d0db |
completed | March 7, 2026, 12:24 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ac195b7cd08190b2c3f07d7ae849ed |
completed | March 7, 2026, 12:26 p.m. |
Created at: March 1, 2026, 7:40 p.m.