Triple
T23145806
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deram Records |
E577580
|
entity |
| Predicate | cataloguePrefix |
P43716
|
FINISHED |
| Object |
SML
SML is a catalogue prefix used by Deram Records to identify a specific series of its music releases.
|
E1574678
|
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: SML | Statement: [Deram Records, cataloguePrefix, SML]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SML Context triple: [Deram Records, cataloguePrefix, SML]
-
A.
SML
SML is the station code for Shimla railway station, a terminus of the historic Kalka–Shimla narrow-gauge mountain railway in Himachal Pradesh, India.
-
B.
SML
SML is the three-letter National Rail station code assigned to Sea Mills railway station in Bristol, England.
-
C.
SML
SML is the abbreviation for Shoals Marine Laboratory, a field-based marine science education and research facility located on Appledore Island in the Gulf of Maine.
-
D.
Standard ML
Standard ML is a statically typed functional programming language with type inference and a formal semantics, widely used in programming language research and teaching.
-
E.
SML/NJ
SML/NJ is a widely used, open-source compiler and interactive environment for the Standard ML programming language, known for its robust type system support and advanced compilation technology.
- 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: SML Triple: [Deram Records, cataloguePrefix, SML]
Generated description
SML is a catalogue prefix used by Deram Records to identify a specific series of its music releases.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: SML Target entity description: SML is a catalogue prefix used by Deram Records to identify a specific series of its music releases.
-
A.
SML
SML is the station code for Shimla railway station, a terminus of the historic Kalka–Shimla narrow-gauge mountain railway in Himachal Pradesh, India.
-
B.
SML
SML is the three-letter National Rail station code assigned to Sea Mills railway station in Bristol, England.
-
C.
SML
SML is the abbreviation for Shoals Marine Laboratory, a field-based marine science education and research facility located on Appledore Island in the Gulf of Maine.
-
D.
Standard ML
Standard ML is a statically typed functional programming language with type inference and a formal semantics, widely used in programming language research and teaching.
-
E.
SML/NJ
SML/NJ is a widely used, open-source compiler and interactive environment for the Standard ML programming language, known for its robust type system support and advanced compilation technology.
- 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_69e245f8e6248190ba3d58e068b4dccb |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18ece211c81908b53e98f0acae09a |
completed | April 29, 2026, 4:53 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c3093de588190bafd130d38fb8d01 |
completed | May 19, 2026, 9:42 a.m. |
| NEDg | Description generation | batch_6a0c351d75a881909f30bc078035f1eb |
completed | May 19, 2026, 10:02 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c359a4fb4819082d923db91b3b14b |
completed | May 19, 2026, 10:04 a.m. |
Created at: April 17, 2026, 4:01 p.m.