Triple
T21501821
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Westbourne Park Underground station |
E530492
|
entity |
| Predicate | hasStationCode |
P1289
|
FINISHED |
| Object |
WBP
WBP is the three-letter station code used to identify Westbourne Park station on the London Underground network.
|
E1488365
|
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: WBP | Statement: [Westbourne Park Underground station, hasStationCode, WBP]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: WBP Context triple: [Westbourne Park Underground station, hasStationCode, WBP]
-
A.
West Bengal
West Bengal is an eastern Indian state known for its cultural heritage, literature, and the metropolis of Kolkata (formerly Calcutta).
-
B.
Bihar
Bihar is a populous state in eastern India known for its rich historical heritage, including ancient centers of learning like Nalanda and significant sites in Buddhist history.
-
C.
Bihar
Bihar is a historical region in Central Europe that once formed part of the Kingdom of Hungary and now lies divided mainly between eastern Hungary and western Romania.
-
D.
Assam
Assam is a northeastern region of the Indian subcontinent known for its tea plantations, rich biodiversity, and distinct cultural heritage.
-
E.
Tripura
Tripura is a small, hilly state in northeastern India known for its diverse tribal cultures, historical palaces, and dense forests.
- 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: WBP Triple: [Westbourne Park Underground station, hasStationCode, WBP]
Generated description
WBP is the three-letter station code used to identify Westbourne Park station on the London Underground network.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: WBP Target entity description: WBP is the three-letter station code used to identify Westbourne Park station on the London Underground network.
-
A.
West Bengal
West Bengal is an eastern Indian state known for its cultural heritage, literature, and the metropolis of Kolkata (formerly Calcutta).
-
B.
Bihar
Bihar is a populous state in eastern India known for its rich historical heritage, including ancient centers of learning like Nalanda and significant sites in Buddhist history.
-
C.
Bihar
Bihar is a historical region in Central Europe that once formed part of the Kingdom of Hungary and now lies divided mainly between eastern Hungary and western Romania.
-
D.
Assam
Assam is a northeastern region of the Indian subcontinent known for its tea plantations, rich biodiversity, and distinct cultural heritage.
-
E.
Tripura
Tripura is a small, hilly state in northeastern India known for its diverse tribal cultures, historical palaces, and dense forests.
- 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_69e0c45bd15481909fba5910765cdda2 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea5d209881908754eb07a47e478a |
completed | April 23, 2026, 9:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09e13f716881909ec0aeebf9932fca |
completed | May 17, 2026, 3:39 p.m. |
| NEDg | Description generation | batch_6a09e55c71f88190b46b6652d29bc02b |
completed | May 17, 2026, 3:57 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a09e5bd9be0819084db29a639f117fc |
completed | May 17, 2026, 3:58 p.m. |
Created at: April 16, 2026, 6:24 p.m.