Triple
T19933524
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Balint |
E479115
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Alice Balint
Alice Balint was a Hungarian psychoanalyst known for her contributions to child psychology and early object-relations theory.
|
E1402610
|
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: Alice Balint | Statement: [Michael Balint, spouse, Alice Balint]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alice Balint Context triple: [Michael Balint, spouse, Alice Balint]
-
A.
Judith Mihalyi
Judith Mihalyi is best known as the wife of American actor René Auberjonois, recognized for his extensive work in film, television, and theater.
-
B.
Judith Olah
Judith Olah is best known as the wife of Nobel Prize–winning chemist George A. Olah.
-
C.
Katalin Ladik
Katalin Ladik is a Serbian-Hungarian poet, performance artist, and actress known for her experimental sound poetry and avant-garde multimedia work.
-
D.
Ruzena Bajcsy
Ruzena Bajcsy is a pioneering computer scientist and engineer known for her influential work in robotics, computer vision, and artificial intelligence.
-
E.
Barbara Czakó
Barbara Czakó is a chemist and co-author of the textbook "Molecules and Medicine," which explores the chemistry underlying modern pharmaceuticals and therapeutics.
- 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: Alice Balint Triple: [Michael Balint, spouse, Alice Balint]
Generated description
Alice Balint was a Hungarian psychoanalyst known for her contributions to child psychology and early object-relations theory.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Alice Balint Target entity description: Alice Balint was a Hungarian psychoanalyst known for her contributions to child psychology and early object-relations theory.
-
A.
Judith Mihalyi
Judith Mihalyi is best known as the wife of American actor René Auberjonois, recognized for his extensive work in film, television, and theater.
-
B.
Judith Olah
Judith Olah is best known as the wife of Nobel Prize–winning chemist George A. Olah.
-
C.
Katalin Ladik
Katalin Ladik is a Serbian-Hungarian poet, performance artist, and actress known for her experimental sound poetry and avant-garde multimedia work.
-
D.
Ruzena Bajcsy
Ruzena Bajcsy is a pioneering computer scientist and engineer known for her influential work in robotics, computer vision, and artificial intelligence.
-
E.
Barbara Czakó
Barbara Czakó is a chemist and co-author of the textbook "Molecules and Medicine," which explores the chemistry underlying modern pharmaceuticals and therapeutics.
- 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_69d8e521855c8190b41871700afc8d6a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65a1553348190a6c4004d3f9a57c5 |
completed | April 20, 2026, 4:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a07f6e639788190a63c52cf284dbe99 |
completed | May 16, 2026, 4:47 a.m. |
| NEDg | Description generation | batch_6a07f7d235688190971c9c0063669470 |
completed | May 16, 2026, 4:51 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a07f891e5c081909e30e9ce7c271359 |
completed | May 16, 2026, 4:54 a.m. |
Created at: April 10, 2026, 1:53 p.m.