Triple
T9862405
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Old Broad Street |
E239746
|
entity |
| Predicate | hasBuilding |
P105
|
FINISHED |
| Object |
Tower 42
Tower 42 is a prominent modernist skyscraper in the City of London, formerly known as the NatWest Tower and once the tallest building in the United Kingdom.
|
E826159
|
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: Tower 42 | Statement: [Old Broad Street, hasBuilding, Tower 42]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tower 42 Context triple: [Old Broad Street, hasBuilding, Tower 42]
-
A.
Tower 2000
Tower 2000 is a high-rise office and business complex that forms part of Moscow’s modern Moscow International Business Center skyline.
-
B.
Tower Forty-seven
Tower Forty-seven is one of the defensive towers incorporated into the historic medieval York city walls in York, England.
-
C.
Tower Forty
Tower Forty is one of the numbered defensive towers incorporated into the historic medieval city walls of York, England.
-
D.
Infinity Tower
Infinity Tower, now known as Cayan Tower, is a distinctive 75-story residential skyscraper in Dubai famous for its 90-degree twisting design.
-
E.
Torre
Torre is a neighborhood in the Brazilian city of Recife, known for its residential character and urban amenities.
- 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: Tower 42 Triple: [Old Broad Street, hasBuilding, Tower 42]
Generated description
Tower 42 is a prominent modernist skyscraper in the City of London, formerly known as the NatWest Tower and once the tallest building in the United Kingdom.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tower 42 Target entity description: Tower 42 is a prominent modernist skyscraper in the City of London, formerly known as the NatWest Tower and once the tallest building in the United Kingdom.
-
A.
Tower 2000
Tower 2000 is a high-rise office and business complex that forms part of Moscow’s modern Moscow International Business Center skyline.
-
B.
Tower Forty-seven
Tower Forty-seven is one of the defensive towers incorporated into the historic medieval York city walls in York, England.
-
C.
Tower Forty
Tower Forty is one of the numbered defensive towers incorporated into the historic medieval city walls of York, England.
-
D.
Infinity Tower
Infinity Tower, now known as Cayan Tower, is a distinctive 75-story residential skyscraper in Dubai famous for its 90-degree twisting design.
-
E.
Torre
Torre is a neighborhood in the Brazilian city of Recife, known for its residential character and urban amenities.
- 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_69ca84e6493081909cf58c8d42ea856b |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb3b7b81c81909a84f6ced829f394 |
completed | April 2, 2026, 12:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1e447d3dc819090268f7d14ba3be4 |
completed | April 5, 2026, 4:25 a.m. |
| NEDg | Description generation | batch_69d1e4bdd10881909d03bac4912e8e0a |
completed | April 5, 2026, 4:27 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d1e5358b148190a6e432aac9d02544 |
completed | April 5, 2026, 4:29 a.m. |
Created at: March 30, 2026, 8:35 p.m.