Triple
T15078898
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Russel Crouse |
E380082
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Anna Erskine
Anna Erskine was the wife of American playwright and producer Russel Crouse, associated with the mid-20th-century Broadway theater world.
|
E300342
|
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: Anna Erskine | Statement: [Russel Crouse, spouse, Anna Erskine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Anna Erskine Context triple: [Russel Crouse, spouse, Anna Erskine]
-
A.
Anna Erskine
Anna Erskine is the daughter of American actress Lindsay Crouse.
-
B.
Elisabeth Farquharson
Elisabeth Farquharson was an 18th-century Scottish gentlewoman best known as the wife of the jurist and early evolutionary thinker James Burnett, Lord Monboddo.
-
C.
Margaret Lindsay
Margaret Lindsay was an American film actress of the 1930s and 1940s, known for her supporting roles in numerous Hollywood dramas and crime films.
-
D.
Margaret Lindsay
Margaret Lindsay was a Scottish noblewoman best known as the wife of David Carnegie, 1st Earl of Southesk, and a member of the influential Lindsay family.
-
E.
Elizabeth Macdowall
Elizabeth Macdowall was the wife of Scottish judge and memoirist Henry Cockburn, Lord Cockburn, and a member of Edinburgh’s early 19th-century legal and social circles.
- 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: Anna Erskine Triple: [Russel Crouse, spouse, Anna Erskine]
Generated description
Anna Erskine was the wife of American playwright and producer Russel Crouse, associated with the mid-20th-century Broadway theater world.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Anna Erskine Target entity description: Anna Erskine was the wife of American playwright and producer Russel Crouse, associated with the mid-20th-century Broadway theater world.
-
A.
Anna Erskine
chosen
Anna Erskine is the daughter of American actress Lindsay Crouse.
-
B.
Elisabeth Farquharson
Elisabeth Farquharson was an 18th-century Scottish gentlewoman best known as the wife of the jurist and early evolutionary thinker James Burnett, Lord Monboddo.
-
C.
Margaret Lindsay
Margaret Lindsay was an American film actress of the 1930s and 1940s, known for her supporting roles in numerous Hollywood dramas and crime films.
-
D.
Margaret Lindsay
Margaret Lindsay was a Scottish noblewoman best known as the wife of David Carnegie, 1st Earl of Southesk, and a member of the influential Lindsay family.
-
E.
Elizabeth Macdowall
Elizabeth Macdowall was the wife of Scottish judge and memoirist Henry Cockburn, Lord Cockburn, and a member of Edinburgh’s early 19th-century legal and social circles.
- F. None of above.
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_69d85cd7683881908d405c1b5d7b4f7f |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69dff7fe5a208190823900b25e298dab |
completed | April 15, 2026, 8:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69feb7dfae748190a0d59df5cbd5787d |
completed | May 9, 2026, 4:28 a.m. |
| NEDg | Description generation | batch_69feb945ec7481909f4bfbf628985af8 |
completed | May 9, 2026, 4:34 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69feb9a010ec819087df75319550cc88 |
completed | May 9, 2026, 4:35 a.m. |
Created at: April 10, 2026, 3:03 a.m.