Triple
T13075491
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Croydon town centre |
E329561
|
entity |
| Predicate | hasOfficeBuilding |
P4847
|
FINISHED |
| Object |
City House
City House is a commercial office building located in Croydon town centre in South London.
|
E1019364
|
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: City House | Statement: [Croydon town centre, hasOfficeBuilding, City House]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: City House Context triple: [Croydon town centre, hasOfficeBuilding, City House]
-
A.
World-Wide House
World-Wide House is a prominent commercial office and retail building in Central, Hong Kong, known for its bustling arcade of small shops and services.
-
B.
Market House
Market House is a historic civic building in the town of Lisnaskea, County Fermanagh, traditionally used as a focal point for local trade and community gatherings.
-
C.
The Town Hall
The Town Hall is a historic performance venue in Midtown Manhattan, New York City, renowned for its concerts, lectures, and cultural events.
-
D.
Shell House
Shell House was the former Johannesburg headquarters of South Africa’s African National Congress, later renamed Luthuli House.
-
E.
Chelsea Tower
Chelsea Tower is one of the main high-rise accommodation towers within The Cosmopolitan of Las Vegas resort on the Las Vegas Strip.
- 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: City House Triple: [Croydon town centre, hasOfficeBuilding, City House]
Generated description
City House is a commercial office building located in Croydon town centre in South London.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: City House Target entity description: City House is a commercial office building located in Croydon town centre in South London.
-
A.
World-Wide House
World-Wide House is a prominent commercial office and retail building in Central, Hong Kong, known for its bustling arcade of small shops and services.
-
B.
Market House
Market House is a historic civic building in the town of Lisnaskea, County Fermanagh, traditionally used as a focal point for local trade and community gatherings.
-
C.
The Town Hall
The Town Hall is a historic performance venue in Midtown Manhattan, New York City, renowned for its concerts, lectures, and cultural events.
-
D.
Shell House
Shell House was the former Johannesburg headquarters of South Africa’s African National Congress, later renamed Luthuli House.
-
E.
Chelsea Tower
Chelsea Tower is one of the main high-rise accommodation towers within The Cosmopolitan of Las Vegas resort on the Las Vegas Strip.
- 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_69d80771749c81909a6d9197b9504872 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d98117209081908272021013df2222 |
completed | April 10, 2026, 11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6d608a2288190bf07023a5303f887 |
completed | May 3, 2026, 4:58 a.m. |
| NEDg | Description generation | batch_69f6d6e326408190b7906c7ea8e3ef85 |
completed | May 3, 2026, 5:02 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69f6d873b978819097962c82e8ffdac8 |
completed | May 3, 2026, 5:09 a.m. |
Created at: April 9, 2026, 9 p.m.