Triple
T20172764
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Westferry Road |
E492008
|
entity |
| Predicate | hasBusRoute |
P39381
|
FINISHED |
| Object |
D3
D3 is a London bus route that operates in the East London area, connecting residential neighborhoods with key transport hubs and commercial districts.
|
E1415427
|
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: D3 | Statement: [Westferry Road, hasBusRoute, D3]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: D3 Context triple: [Westferry Road, hasBusRoute, D3]
-
A.
D3
D3 is the internal designation for the second-generation Audi A8 luxury sedan, produced in the mid-2000s and known for its aluminum space frame construction and advanced technology features.
-
B.
D3
D3 is one of the commuter rail lines of the Moscow Central Diameters urban rail system, connecting Moscow with its surrounding suburbs.
-
C.
D3
D3 is the commonly used abbreviation for California Department of Transportation's District 3, which oversees state transportation infrastructure in part of Northern California.
-
D.
D3
D3 is the station code assigned to the Wilshire/Normandie station on the Los Angeles Metro Rail system.
-
E.
d3
d3 is a purpose-built creative hub in Dubai that fosters design, fashion, art, and innovation through studios, galleries, offices, and community events.
- 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: D3 Triple: [Westferry Road, hasBusRoute, D3]
Generated description
D3 is a London bus route that operates in the East London area, connecting residential neighborhoods with key transport hubs and commercial districts.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: D3 Target entity description: D3 is a London bus route that operates in the East London area, connecting residential neighborhoods with key transport hubs and commercial districts.
-
A.
D3
D3 is one of the commuter rail lines of the Moscow Central Diameters urban rail system, connecting Moscow with its surrounding suburbs.
-
B.
D3
D3 is the commonly used abbreviation for California Department of Transportation's District 3, which oversees state transportation infrastructure in part of Northern California.
-
C.
D3
D3 is the internal designation for the second-generation Audi A8 luxury sedan, produced in the mid-2000s and known for its aluminum space frame construction and advanced technology features.
-
D.
D3
D3 is the station code assigned to the Wilshire/Normandie station on the Los Angeles Metro Rail system.
-
E.
d3
d3 is a purpose-built creative hub in Dubai that fosters design, fashion, art, and innovation through studios, galleries, offices, and community events.
- 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_69da6266c6888190bc1a3ecf24814d34 |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e66849709c81909b65b421282f9f3b |
completed | April 20, 2026, 5:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a083484eaa4819083462003ba5a78b0 |
completed | May 16, 2026, 9:10 a.m. |
| NEDg | Description generation | batch_6a083851ccf081909de87d5070e969f9 |
completed | May 16, 2026, 9:26 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0838c3694c819097516c8de60864fb |
completed | May 16, 2026, 9:28 a.m. |
Created at: April 11, 2026, 11:35 p.m.