Triple
T5338973
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Columbo |
E123896
|
entity |
| Predicate | createdBy |
P806
|
FINISHED |
| Object |
Richard Levinson
Richard Levinson was an American television writer and producer best known for co-creating the iconic detective series Columbo.
|
E511298
|
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: Richard Levinson | Statement: [Columbo, createdBy, Richard Levinson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Richard Levinson Context triple: [Columbo, createdBy, Richard Levinson]
-
A.
Arthur D. Levinson
Arthur D. Levinson is an American biochemist and business executive best known as the longtime CEO of Genentech and the chairman of Apple Inc.'s board of directors.
-
B.
Edward K. Milkis
Edward K. Milkis was an American television producer best known for his work on popular 1970s sitcoms and collaborations with Garry Marshall.
-
C.
Stephen Levinson
Stephen Levinson is an American television and film producer and talent manager best known for producing hit series like "Entourage" and "Ballers."
-
D.
Robert Wachs
Robert Wachs is a film producer best known for his work on the comedy film "Delirious."
-
E.
Robert D. Wachs
Robert D. Wachs was a film and television producer best known for his work on the hit comedy "Coming to 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: Richard Levinson Triple: [Columbo, createdBy, Richard Levinson]
Generated description
Richard Levinson was an American television writer and producer best known for co-creating the iconic detective series Columbo.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Richard Levinson Target entity description: Richard Levinson was an American television writer and producer best known for co-creating the iconic detective series Columbo.
-
A.
Arthur D. Levinson
Arthur D. Levinson is an American biochemist and business executive best known as the longtime CEO of Genentech and the chairman of Apple Inc.'s board of directors.
-
B.
Edward K. Milkis
Edward K. Milkis was an American television producer best known for his work on popular 1970s sitcoms and collaborations with Garry Marshall.
-
C.
Stephen Levinson
Stephen Levinson is an American television and film producer and talent manager best known for producing hit series like "Entourage" and "Ballers."
-
D.
Robert Wachs
Robert Wachs is a film producer best known for his work on the comedy film "Delirious."
-
E.
Robert D. Wachs
Robert D. Wachs was a film and television producer best known for his work on the hit comedy "Coming to 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_69bd464b07f8819095aa76577c9829e4 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd85c8415c819099a0b26e07360f01 |
completed | March 20, 2026, 5:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf18c54ca4819095ca1d81ee061937 |
completed | March 21, 2026, 10:16 p.m. |
| NEDg | Description generation | batch_69bf197733b48190910bdd60fbd94fff |
completed | March 21, 2026, 10:19 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69bf19e2d1fc81909030e32bb18d46dc |
completed | March 21, 2026, 10:21 p.m. |
Created at: March 20, 2026, 2 p.m.