Triple
T8421750
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Steve Holmes |
E198870
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Petra Holmes
Petra Holmes is known as the wife of Steve Holmes.
|
E733093
|
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: Petra Holmes | Statement: [Steve Holmes, spouse, Petra Holmes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Petra Holmes Context triple: [Steve Holmes, spouse, Petra Holmes]
-
A.
Susanna Reid
Susanna Reid is a British television presenter and journalist best known as a long-time breakfast show host on BBC Breakfast and Good Morning Britain.
-
B.
Elizabeth Dauncey
Elizabeth Dauncey was the wife of American screenwriter Waldemar Young, known primarily through her marriage to this prominent Hollywood figure.
-
C.
Katie Normington
Katie Normington is a British academic and higher education leader who serves as the Vice-Chancellor of De Montfort University.
-
D.
Sue Lawley
Sue Lawley is a British broadcaster and journalist best known for her long-running role as host of the BBC radio programme Desert Island Discs.
-
E.
Caroline Waterlow
Caroline Waterlow is an American film and television producer best known for her work on acclaimed documentaries, including the Oscar-winning series "O.J.: Made in America."
- 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: Petra Holmes Triple: [Steve Holmes, spouse, Petra Holmes]
Generated description
Petra Holmes is known as the wife of Steve Holmes.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Petra Holmes Target entity description: Petra Holmes is known as the wife of Steve Holmes.
-
A.
Susanna Reid
Susanna Reid is a British television presenter and journalist best known as a long-time breakfast show host on BBC Breakfast and Good Morning Britain.
-
B.
Elizabeth Dauncey
Elizabeth Dauncey was the wife of American screenwriter Waldemar Young, known primarily through her marriage to this prominent Hollywood figure.
-
C.
Katie Normington
Katie Normington is a British academic and higher education leader who serves as the Vice-Chancellor of De Montfort University.
-
D.
Sue Lawley
Sue Lawley is a British broadcaster and journalist best known for her long-running role as host of the BBC radio programme Desert Island Discs.
-
E.
Caroline Waterlow
Caroline Waterlow is an American film and television producer best known for her work on acclaimed documentaries, including the Oscar-winning series "O.J.: Made in America."
- 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_69ca8312d63c8190bf133b676b44a385 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cb859e22f88190a61e7dd6537644b0 |
completed | March 31, 2026, 8:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce035279f48190861b97167fa3882c |
completed | April 2, 2026, 5:49 a.m. |
| NEDg | Description generation | batch_69ce07837648819080cd4026af55b246 |
completed | April 2, 2026, 6:06 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ce083cee848190b27a7dd19a16a0dc |
completed | April 2, 2026, 6:10 a.m. |
Created at: March 30, 2026, 6:06 p.m.