Triple
T15700289
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Royal Bank Plaza |
E380574
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object |
North Tower
North Tower is one of the two prominent office skyscrapers that make up Toronto’s Royal Bank Plaza complex.
|
E1174388
|
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: North Tower | Statement: [Royal Bank Plaza, hasPart, North Tower]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: North Tower Context triple: [Royal Bank Plaza, hasPart, North Tower]
-
A.
North Tower
North Tower is a prominent residential skyscraper within the Deansgate Square complex in Manchester, England.
-
B.
North Tower
North Tower is a high-rise office and commercial skyscraper within Moscow's International Business Center complex.
-
C.
North Tower
North Tower is one of the twin skyscraper components of New York City's Time Warner Center complex, housing offices, residences, and commercial spaces.
-
D.
North Tower
The North Tower is a remote, high turret at Hogwarts School of Witchcraft and Wizardry, best known as the site of Professor Sybill Trelawney’s Divination classroom.
-
E.
South Tower
South Tower is one of the twin skyscraper components of Manhattan’s Time Warner Center complex, housing luxury residences, offices, and commercial spaces overlooking Columbus Circle.
- 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: North Tower Triple: [Royal Bank Plaza, hasPart, North Tower]
Generated description
North Tower is one of the two prominent office skyscrapers that make up Toronto’s Royal Bank Plaza complex.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: North Tower Target entity description: North Tower is one of the two prominent office skyscrapers that make up Toronto’s Royal Bank Plaza complex.
-
A.
North Tower
The North Tower is a remote, high turret at Hogwarts School of Witchcraft and Wizardry, best known as the site of Professor Sybill Trelawney’s Divination classroom.
-
B.
North Tower
North Tower is a prominent residential skyscraper within the Deansgate Square complex in Manchester, England.
-
C.
North Tower
North Tower is a high-rise office and commercial skyscraper within Moscow's International Business Center complex.
-
D.
North Tower
North Tower is one of the twin skyscraper components of New York City's Time Warner Center complex, housing offices, residences, and commercial spaces.
-
E.
South Tower
South Tower is one of the twin skyscraper components of Manhattan’s Time Warner Center complex, housing luxury residences, offices, and commercial spaces overlooking Columbus Circle.
- 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_69d86d99e860819094b6957cde470f2c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04f6d71308190971c10c599da9645 |
completed | April 16, 2026, 2:54 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff82ee580c819082ad53db6da91f66 |
completed | May 9, 2026, 6:54 p.m. |
| NEDg | Description generation | batch_69ff83b7a534819090e24491579376c3 |
completed | May 9, 2026, 6:57 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ff844fa00c8190a47eb46394db097b |
completed | May 9, 2026, 7 p.m. |
Created at: April 10, 2026, 4:45 a.m.