Triple
T17662424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Unbridled |
E440284
|
entity |
| Predicate | notableProgeny |
P50188
|
FINISHED |
| Object |
Red Bullet
Red Bullet is an American Thoroughbred racehorse best known for winning the 2000 Preakness Stakes, the second leg of the U.S. Triple Crown.
|
E1281587
|
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: Red Bullet | Statement: [Unbridled, notableProgeny, Red Bullet]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Red Bullet Context triple: [Unbridled, notableProgeny, Red Bullet]
-
A.
Bullett
Bullett is a surname most notably associated with Vicky Bullett, a former American professional basketball player and Olympic gold medalist.
-
B.
Bullshot
Bullshot is a 1983 British comedy film that parodies 1930s adventure serials and detective stories, produced by HandMade Films.
-
C.
The Bullet
The Bullet is a song by Carrie Underwood from her album "Cry Pretty," noted for its emotional storytelling and country-pop style.
-
D.
Live Bullet
Live Bullet is a celebrated live rock album by Bob Seger & the Silver Bullet Band, widely credited with breaking Seger into national prominence in the mid-1970s.
-
E.
Bullets
Bullets is the commonly used short name for the Brisbane Bullets, a professional basketball team in Australia's National Basketball League.
- 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: Red Bullet Triple: [Unbridled, notableProgeny, Red Bullet]
Generated description
Red Bullet is an American Thoroughbred racehorse best known for winning the 2000 Preakness Stakes, the second leg of the U.S. Triple Crown.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Red Bullet Target entity description: Red Bullet is an American Thoroughbred racehorse best known for winning the 2000 Preakness Stakes, the second leg of the U.S. Triple Crown.
-
A.
Bullett
Bullett is a surname most notably associated with Vicky Bullett, a former American professional basketball player and Olympic gold medalist.
-
B.
Bullshot
Bullshot is a 1983 British comedy film that parodies 1930s adventure serials and detective stories, produced by HandMade Films.
-
C.
The Bullet
The Bullet is a song by Carrie Underwood from her album "Cry Pretty," noted for its emotional storytelling and country-pop style.
-
D.
Live Bullet
Live Bullet is a celebrated live rock album by Bob Seger & the Silver Bullet Band, widely credited with breaking Seger into national prominence in the mid-1970s.
-
E.
Bullets
Bullets is the commonly used short name for the Brisbane Bullets, a professional basketball team in Australia's National Basketball League.
- 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_69d8b9e87e18819087104a44dc4dc5b1 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e46ea73c90819087a23a7b6171f581 |
completed | April 19, 2026, 5:56 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a02165c9a4481909a6c43b2b58e1fc8 |
completed | May 11, 2026, 5:48 p.m. |
| NEDg | Description generation | batch_6a021f80092c81909a1827561ed69f17 |
completed | May 11, 2026, 6:27 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a021fe90da48190810c7aa2c2de2801 |
completed | May 11, 2026, 6:28 p.m. |
Created at: April 10, 2026, 9:48 a.m.