Triple
T7662880
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ruth First |
E173549
|
entity |
| Predicate | parent |
P120
|
FINISHED |
| Object |
Matilda Levetan First
Matilda Levetan First is the daughter of South African anti-apartheid activist and journalist Ruth First.
|
E680058
|
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: Matilda Levetan First | Statement: [Ruth First, parent, Matilda Levetan First]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Matilda Levetan First Context triple: [Ruth First, parent, Matilda Levetan First]
-
A.
Matilda Shapiro
Matilda Shapiro was the wife of Polish-Jewish novelist and playwright Sholem Asch, a prominent figure in Yiddish literature.
-
B.
Beatrice Pearl Levy
Beatrice Pearl Levy was the first wife of acclaimed British actor Claude Rains, to whom he was married early in his career.
-
C.
Miriam Bienstock
Miriam Bienstock was an American music industry executive and co-founder of Atlantic Records who played a key role in shaping the label’s early business operations and success.
-
D.
Beatrice Selinger
Beatrice Selinger was the wife of American silent film comedian Charley Chase.
-
E.
Miriam Mendelsohn
Miriam Mendelsohn is a loyal, upbeat, and supportive best friend of Mei Lee in Pixar's animated film "Turning Red."
- 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: Matilda Levetan First Triple: [Ruth First, parent, Matilda Levetan First]
Generated description
Matilda Levetan First is the daughter of South African anti-apartheid activist and journalist Ruth First.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Matilda Levetan First Target entity description: Matilda Levetan First is the daughter of South African anti-apartheid activist and journalist Ruth First.
-
A.
Matilda Shapiro
Matilda Shapiro was the wife of Polish-Jewish novelist and playwright Sholem Asch, a prominent figure in Yiddish literature.
-
B.
Beatrice Pearl Levy
Beatrice Pearl Levy was the first wife of acclaimed British actor Claude Rains, to whom he was married early in his career.
-
C.
Miriam Bienstock
Miriam Bienstock was an American music industry executive and co-founder of Atlantic Records who played a key role in shaping the label’s early business operations and success.
-
D.
Beatrice Selinger
Beatrice Selinger was the wife of American silent film comedian Charley Chase.
-
E.
Miriam Mendelsohn
Miriam Mendelsohn is a loyal, upbeat, and supportive best friend of Mei Lee in Pixar's animated film "Turning Red."
- 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_69c69955517c819085bc715b96d304d2 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c701a74a2c81909f78ab2de7ce807c |
completed | March 27, 2026, 10:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c89b1aaef081908d1d181ea7c28c2f |
completed | March 29, 2026, 3:23 a.m. |
| NEDg | Description generation | batch_69c89e177fd08190a6f3a70cf32365d9 |
completed | March 29, 2026, 3:35 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c89e7328f4819088651b60e7af457d |
completed | March 29, 2026, 3:37 a.m. |
Created at: March 27, 2026, 3:59 p.m.