Triple
T1641621
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | University of Bristol |
E35482
|
entity |
| Predicate | hasNotableAlumni |
P51
|
FINISHED |
| Object |
Amy Williams
Amy Williams is a British skeleton racer who won the gold medal at the 2010 Winter Olympics in Vancouver.
|
E237012
|
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: Amy Williams | Statement: [University of Bristol, hasNotableAlumni, Amy Williams]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Amy Williams Context triple: [University of Bristol, hasNotableAlumni, Amy Williams]
-
A.
Ann Williams
Ann Williams is an American dancer, choreographer, and arts educator best known as the founder and longtime artistic director of the Dallas Black Dance Theatre.
-
B.
Mary Williams
Mary Williams was the wife of American planter and statesman Henry Middleton, a prominent figure in colonial South Carolina.
-
C.
Jennifer Williams
Jennifer Williams is known as the daughter of acclaimed American composer and conductor John Williams.
-
D.
Emily Carmichael
Emily Carmichael is an American filmmaker and screenwriter known for her work on genre films such as Pacific Rim: Uprising and for her distinctive, imaginative storytelling style.
-
E.
Laura Jones
Laura Jones is an Australian screenwriter known for her work on acclaimed films such as "High Tide" (1987) and several literary adaptations.
- 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: Amy Williams Triple: [University of Bristol, hasNotableAlumni, Amy Williams]
Generated description
Amy Williams is a British skeleton racer who won the gold medal at the 2010 Winter Olympics in Vancouver.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Amy Williams Target entity description: Amy Williams is a British skeleton racer who won the gold medal at the 2010 Winter Olympics in Vancouver.
-
A.
Ann Williams
Ann Williams is an American dancer, choreographer, and arts educator best known as the founder and longtime artistic director of the Dallas Black Dance Theatre.
-
B.
Mary Williams
Mary Williams was the wife of American planter and statesman Henry Middleton, a prominent figure in colonial South Carolina.
-
C.
Jennifer Williams
Jennifer Williams is known as the daughter of acclaimed American composer and conductor John Williams.
-
D.
Emily Carmichael
Emily Carmichael is an American filmmaker and screenwriter known for her work on genre films such as Pacific Rim: Uprising and for her distinctive, imaginative storytelling style.
-
E.
Laura Jones
Laura Jones is an Australian screenwriter known for her work on acclaimed films such as "High Tide" (1987) and several literary adaptations.
- 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_69a88604618c81908b41f6429c431eb6 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a90a3e254081908b7c4a9dfeafc4f8 |
completed | March 5, 2026, 4:44 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae516742dc81909915c49b12645c26 |
completed | March 9, 2026, 4:49 a.m. |
| NEDg | Description generation | batch_69ae524946f881908452e7f414962e70 |
completed | March 9, 2026, 4:53 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ae529f2e508190b7483b70c9dbf9f9 |
completed | March 9, 2026, 4:54 a.m. |
Created at: March 4, 2026, 7:28 p.m.