Triple
T1371049
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Collingwood Football Club |
E30112
|
entity |
| Predicate | coach |
P2169
|
FINISHED |
| Object |
Craig McRae
Craig McRae is an Australian rules football coach and former player best known for leading the Collingwood Football Club to an AFL premiership.
|
E158320
|
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: Craig McRae | Statement: [Collingwood Football Club, coach, Craig McRae]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Craig McRae Context triple: [Collingwood Football Club, coach, Craig McRae]
-
A.
Charlie MacLean
Charlie MacLean is a television writer and producer best known for creating the crime drama series "City on a Hill."
-
B.
Ewen MacAskill
Ewen MacAskill is a Scottish journalist and former Guardian reporter known for helping reveal Edward Snowden’s NSA surveillance leaks.
-
C.
Gawen Lawrie
Gawen Lawrie was a 17th-century English Quaker and colonial proprietor who played a key role in the early settlement and governance of West Jersey in North America.
-
D.
Laird Doyle
Laird Doyle was an American screenwriter active in early Hollywood, known for adapting literary works for the screen.
-
E.
Dougie
Dougie is a familiar diminutive form of the given name Doug, often used as an affectionate nickname.
- 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: Craig McRae Triple: [Collingwood Football Club, coach, Craig McRae]
Generated description
Craig McRae is an Australian rules football coach and former player best known for leading the Collingwood Football Club to an AFL premiership.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Craig McRae Target entity description: Craig McRae is an Australian rules football coach and former player best known for leading the Collingwood Football Club to an AFL premiership.
-
A.
Charlie MacLean
Charlie MacLean is a television writer and producer best known for creating the crime drama series "City on a Hill."
-
B.
Ewen MacAskill
Ewen MacAskill is a Scottish journalist and former Guardian reporter known for helping reveal Edward Snowden’s NSA surveillance leaks.
-
C.
Gawen Lawrie
Gawen Lawrie was a 17th-century English Quaker and colonial proprietor who played a key role in the early settlement and governance of West Jersey in North America.
-
D.
Laird Doyle
Laird Doyle was an American screenwriter active in early Hollywood, known for adapting literary works for the screen.
-
E.
Dougie
Dougie is a familiar diminutive form of the given name Doug, often used as an affectionate nickname.
- 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_69a498f912008190a376a98b207b2071 |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c2d7b6008190bc0303b56959ba56 |
completed | March 1, 2026, 10:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69acd481de608190bed1dc385209320e |
completed | March 8, 2026, 1:44 a.m. |
| NEDg | Description generation | batch_69acd6a03b70819096bdf7ec3b447756 |
completed | March 8, 2026, 1:53 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69acd71971448190940136b8a44040be |
completed | March 8, 2026, 1:55 a.m. |
Created at: March 1, 2026, 7:57 p.m.