Triple
T22091503
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Christmas Candle |
E545924
|
entity |
| Predicate | editedBy |
P1954
|
FINISHED |
| Object |
David Yardley
David Yardley is an editor known for his work on the book "The Christmas Candle."
|
E1519119
|
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: David Yardley | Statement: [The Christmas Candle, editedBy, David Yardley]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Yardley Context triple: [The Christmas Candle, editedBy, David Yardley]
-
A.
George Yardley
George Yardley was an American Hall of Fame forward best known as one of the NBA’s early scoring stars and the first player to score 2,000 points in a single season.
-
B.
Alastair Denniston
Alastair Denniston was a British naval intelligence officer and pioneering cryptanalyst who played a key leadership role in the development of codebreaking operations that led to Bletchley Park during both World Wars.
-
C.
James Ellis
James Ellis was a Northern Irish actor best known for his long-running role as Bert Lynch in the British television police drama "Z-Cars."
-
D.
John Pollard
John Pollard is a notable individual recognized for his contributions and prominence associated with the Pollard name.
-
E.
John Kelsey
John Kelsey is an American cryptographer known for his contributions to symmetric-key cryptography and the design of several notable encryption algorithms.
- 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: David Yardley Triple: [The Christmas Candle, editedBy, David Yardley]
Generated description
David Yardley is an editor known for his work on the book "The Christmas Candle."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: David Yardley Target entity description: David Yardley is an editor known for his work on the book "The Christmas Candle."
-
A.
George Yardley
George Yardley was an American Hall of Fame forward best known as one of the NBA’s early scoring stars and the first player to score 2,000 points in a single season.
-
B.
Alastair Denniston
Alastair Denniston was a British naval intelligence officer and pioneering cryptanalyst who played a key leadership role in the development of codebreaking operations that led to Bletchley Park during both World Wars.
-
C.
James Ellis
James Ellis was a Northern Irish actor best known for his long-running role as Bert Lynch in the British television police drama "Z-Cars."
-
D.
John Pollard
John Pollard is a notable individual recognized for his contributions and prominence associated with the Pollard name.
-
E.
John Kelsey
John Kelsey is an American cryptographer known for his contributions to symmetric-key cryptography and the design of several notable encryption algorithms.
- 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_69e11e36d03c8190a83a1ba802b7231b |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f128e5edf08190a6743955bc872417 |
completed | April 28, 2026, 9:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0a879b9130819089f8e2b7106f875b |
completed | May 18, 2026, 3:29 a.m. |
| NEDg | Description generation | batch_6a0a891eb0708190a4575a01f45b98aa |
completed | May 18, 2026, 3:35 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0a89977c8c8190a5c87d1c2b68ed48 |
completed | May 18, 2026, 3:37 a.m. |
Created at: April 16, 2026, 8:29 p.m.