Triple
T787668
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marilyn Monroe |
E16840
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
James Dougherty
James Dougherty was an American police officer best known as the first husband of Marilyn Monroe before she became a famous actress.
|
E157862
|
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: James Dougherty | Statement: [Marilyn Monroe, spouse, James Dougherty]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: James Dougherty Context triple: [Marilyn Monroe, spouse, James Dougherty]
-
A.
Michael Callaghan
Michael Callaghan is one of the children of former UK Prime Minister James Callaghan.
-
B.
Kevin O'Connor
Kevin O'Connor is an American entrepreneur best known as the co-founder and former CEO of the online advertising company DoubleClick.
-
C.
Sean McDonough
Sean McDonough is an American sportscaster best known for his long career calling Major League Baseball and college sports on national television.
-
D.
John McGlynn
John McGlynn is a Scottish football manager best known for his successful spells in charge of Raith Rovers.
-
E.
Michael H. Moloney
Michael H. Moloney is a physics-focused science policy and leadership professional who serves as the chief executive officer of the American Institute of Physics.
- 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: James Dougherty Triple: [Marilyn Monroe, spouse, James Dougherty]
Generated description
James Dougherty was an American police officer best known as the first husband of Marilyn Monroe before she became a famous actress.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: James Dougherty Target entity description: James Dougherty was an American police officer best known as the first husband of Marilyn Monroe before she became a famous actress.
-
A.
Michael Callaghan
Michael Callaghan is one of the children of former UK Prime Minister James Callaghan.
-
B.
Kevin O'Connor
Kevin O'Connor is an American entrepreneur best known as the co-founder and former CEO of the online advertising company DoubleClick.
-
C.
Sean McDonough
Sean McDonough is an American sportscaster best known for his long career calling Major League Baseball and college sports on national television.
-
D.
John McGlynn
John McGlynn is a Scottish football manager best known for his successful spells in charge of Raith Rovers.
-
E.
Michael H. Moloney
Michael H. Moloney is a physics-focused science policy and leadership professional who serves as the chief executive officer of the American Institute of Physics.
- 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_69a4936cb7448190914f5fe4b8d81607 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a78171908190a38a70274bfbebf9 |
completed | March 1, 2026, 8:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69acd46422408190911e6eaec5866fe8 |
completed | March 8, 2026, 1:44 a.m. |
| NEDg | Description generation | batch_69acd4fade9881908ed8e4598f4821f6 |
completed | March 8, 2026, 1:46 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69acd55b90608190a5ff734af6264ab5 |
completed | March 8, 2026, 1:48 a.m. |
Created at: March 1, 2026, 7:38 p.m.