Triple
T2883112
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sydney Tower |
E59441
|
entity |
| Predicate | architect |
P184
|
FINISHED |
| Object |
Donald Crone
Donald Crone is an Australian architect best known for designing Sydney’s iconic Sydney Tower.
|
E390070
|
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: Donald Crone | Statement: [Sydney Tower, architect, Donald Crone]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Donald Crone Context triple: [Sydney Tower, architect, Donald Crone]
-
A.
Douglas Crise
Douglas Crise is a film editor best known for his work on acclaimed movies such as "Birdman or (The Unexpected Virtue of Ignorance)."
-
B.
David Scearce
David Scearce is a Canadian screenwriter best known for adapting Christopher Isherwood’s novel into the acclaimed film "A Single Man."
-
C.
Ray Cusick
Ray Cusick was a British designer best known for creating the iconic look of the Daleks in the long-running science fiction television series Doctor Who.
-
D.
Larry Drinkard
Larry Drinkard is a gospel singer best known as a member of the influential family group The Drinkard Singers.
-
E.
Russel Crouse
Russel Crouse was an American playwright, librettist, and producer best known for co-writing the book for the musical "The Sound of Music" as part of the writing team Lindsay and Crouse.
- 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: Donald Crone Triple: [Sydney Tower, architect, Donald Crone]
Generated description
Donald Crone is an Australian architect best known for designing Sydney’s iconic Sydney Tower.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Donald Crone Target entity description: Donald Crone is an Australian architect best known for designing Sydney’s iconic Sydney Tower.
-
A.
Douglas Crise
Douglas Crise is a film editor best known for his work on acclaimed movies such as "Birdman or (The Unexpected Virtue of Ignorance)."
-
B.
David Scearce
David Scearce is a Canadian screenwriter best known for adapting Christopher Isherwood’s novel into the acclaimed film "A Single Man."
-
C.
Ray Cusick
Ray Cusick was a British designer best known for creating the iconic look of the Daleks in the long-running science fiction television series Doctor Who.
-
D.
Larry Drinkard
Larry Drinkard is a gospel singer best known as a member of the influential family group The Drinkard Singers.
-
E.
Russel Crouse
Russel Crouse was an American playwright, librettist, and producer best known for co-writing the book for the musical "The Sound of Music" as part of the writing team Lindsay and Crouse.
- 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_69ab4ac739188190a112f42a5a69c951 |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abe02c238881908f7a349563c388bf |
completed | March 7, 2026, 8:22 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4fad35a0c8190a07cc7877fbfec04 |
completed | March 14, 2026, 6:06 a.m. |
| NEDg | Description generation | batch_69b4fc1d144881908affcdae84a3c395 |
completed | March 14, 2026, 6:11 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b4fc942b588190985b191376289258 |
completed | March 14, 2026, 6:13 a.m. |
Created at: March 6, 2026, 10:03 p.m.