Triple
T3072151
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Atlanta Flames |
E64048
|
entity |
| Predicate | notablePlayer |
P304
|
FINISHED |
| Object |
Tom Lysiak
Tom Lysiak was a Canadian professional ice hockey center best known as a high-scoring star and team captain in the NHL during the 1970s and early 1980s.
|
E327215
|
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: Tom Lysiak | Statement: [Atlanta Flames, notablePlayer, Tom Lysiak]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tom Lysiak Context triple: [Atlanta Flames, notablePlayer, Tom Lysiak]
-
A.
John Cygan
John Cygan was an American actor and voice actor known for his work in animated films, television, and video games.
-
B.
Ronnie Gardocki
Ronnie Gardocki is a member of the Strike Team and a key supporting character in the crime drama television series "The Shield."
-
C.
Pete Kozachik
Pete Kozachik is an American cinematographer best known for his work on stop-motion animated films, including the cult classic "The Nightmare Before Christmas."
-
D.
Joe Pisarcik
Joe Pisarcik is a former NFL quarterback best known for his infamous late-game fumble in 1978 that led to the "Miracle at the Meadowlands."
-
E.
Jon Bosak
Jon Bosak is a computer scientist best known for leading the original XML specification effort at the World Wide Web Consortium (W3C), which helped standardize data interchange on the web.
- 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: Tom Lysiak Triple: [Atlanta Flames, notablePlayer, Tom Lysiak]
Generated description
Tom Lysiak was a Canadian professional ice hockey center best known as a high-scoring star and team captain in the NHL during the 1970s and early 1980s.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tom Lysiak Target entity description: Tom Lysiak was a Canadian professional ice hockey center best known as a high-scoring star and team captain in the NHL during the 1970s and early 1980s.
-
A.
John Cygan
John Cygan was an American actor and voice actor known for his work in animated films, television, and video games.
-
B.
Ronnie Gardocki
Ronnie Gardocki is a member of the Strike Team and a key supporting character in the crime drama television series "The Shield."
-
C.
Pete Kozachik
Pete Kozachik is an American cinematographer best known for his work on stop-motion animated films, including the cult classic "The Nightmare Before Christmas."
-
D.
Joe Pisarcik
Joe Pisarcik is a former NFL quarterback best known for his infamous late-game fumble in 1978 that led to the "Miracle at the Meadowlands."
-
E.
Jon Bosak
Jon Bosak is a computer scientist best known for leading the original XML specification effort at the World Wide Web Consortium (W3C), which helped standardize data interchange on the web.
- 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_69ad857a8aec8190bfdfd9c14554ac5a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada14c8bd881909cf1bb2649ba36db |
completed | March 8, 2026, 4:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b20357f8c48190b6874f7596f30052 |
completed | March 12, 2026, 12:05 a.m. |
| NEDg | Description generation | batch_69b20571792081909fd8eca15a2227fa |
completed | March 12, 2026, 12:14 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b205d86ab0819084a352c0b634a026 |
completed | March 12, 2026, 12:16 a.m. |
Created at: March 8, 2026, 3:02 p.m.