Triple
T8898945
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Baldock |
E211875
|
entity |
| Predicate | postcodeArea |
P920
|
FINISHED |
| Object |
SG
SG is a UK postcode area in the Stevenage region of Hertfordshire and surrounding counties, covering towns such as Baldock, Stevenage, and Hitchin.
|
E209989
|
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: SG | Statement: [Baldock, postcodeArea, SG]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SG Context triple: [Baldock, postcodeArea, SG]
-
A.
SG
SG is the Secretariat-General of the European Commission, the central administrative body that supports the Commission’s work, coordination, and decision-making processes.
-
B.
SG
SG is the IATA airline designator assigned to SpiceJet, a major low-cost carrier based in India.
-
C.
SG
SG is the vehicle registration code used on license plates for the Swiss canton of St. Gallen.
-
D.
SG
SG is the vehicle registration code used on license plates for Spain’s Segovia Province.
-
E.
SG
SG (Sanspareils Greenlands) is a prominent Indian sports equipment manufacturer best known for its high-quality cricket gear, including bats, balls, and protective equipment.
- 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: SG Triple: [Baldock, postcodeArea, SG]
Generated description
SG is a UK postcode area in the Stevenage region of Hertfordshire and surrounding counties, covering towns such as Baldock, Stevenage, and Hitchin.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: SG Target entity description: SG is a UK postcode area in the Stevenage region of Hertfordshire and surrounding counties, covering towns such as Baldock, Stevenage, and Hitchin.
-
A.
SG
chosen
SG is a postcode area in the United Kingdom covering parts of Hertfordshire and surrounding regions.
-
B.
SG
SG is the vehicle registration code used on license plates for Spain’s Segovia Province.
-
C.
SG
SG is the vehicle registration code used on license plates for the Swiss canton of St. Gallen.
-
D.
SG
SG is the IATA airline designator assigned to SpiceJet, a major low-cost carrier based in India.
-
E.
SG
SG (Sanspareils Greenlands) is a prominent Indian sports equipment manufacturer best known for its high-quality cricket gear, including bats, balls, and protective equipment.
- F. None of above.
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_69ca83918d3081909b326fa3750cb8c8 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc642618908190b3df50cbbabff93d |
completed | April 1, 2026, 12:17 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfac10be588190bd1b44f09ded7826 |
completed | April 3, 2026, 12:01 p.m. |
| NEDg | Description generation | batch_69cfacc9b53081909bd3505cff0a7722 |
completed | April 3, 2026, 12:04 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69cfad6fff348190b0491ba38d2e6ce5 |
completed | April 3, 2026, 12:07 p.m. |
Created at: March 30, 2026, 6:54 p.m.