Triple
T3972570
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saliva |
E92366
|
entity |
| Predicate | formerMember |
P1168
|
FINISHED |
| Object | Paul Crosby |
E407156
|
NE FINISHED |
How this triple was built (2 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: Paul Crosby | Statement: [Saliva, formerMember, Paul Crosby]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul Crosby Context triple: [Saliva, formerMember, Paul Crosby]
-
A.
Paul Crosby
chosen
Paul Crosby is an American rock drummer best known for his work with the multi-platinum band Saliva.
-
B.
Gordon Howe
Gordon "Gordie" Howe was a legendary Canadian professional ice hockey player widely known as "Mr. Hockey" and regarded as one of the greatest players in the sport's history.
-
C.
Jim Craig
Jim Craig is an American ice hockey goaltender best known for backstopping the "Miracle on Ice" U.S. team to a gold medal at the 1980 Winter Olympics.
-
D.
Al Schmid
Al Schmid was a highly decorated U.S. Marine and World War II hero whose story of bravery and resilience was dramatized in the film "Pride of the Marines."
-
E.
Bobby Boucher
Bobby Boucher is the socially awkward but hard-hitting college football waterboy-turned-star linebacker portrayed by Adam Sandler in the comedy film "The Waterboy."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69aed96624188190ac8c45bb57ab72b5 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aef996ff6c8190ba8cc490e4744b95 |
completed | March 9, 2026, 4:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5628ab3ec8190aaaf7803f9f992af |
completed | March 14, 2026, 1:28 p.m. |
Created at: March 9, 2026, 3:32 p.m.