Triple
T2967873
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | My Octopus Teacher |
E80208
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object |
Pippa Ehrlich
Pippa Ehrlich is a South African filmmaker and environmental journalist best known for co-directing the Oscar-winning nature documentary "My Octopus Teacher."
|
E322879
|
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: Pippa Ehrlich | Statement: [My Octopus Teacher, director, Pippa Ehrlich]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pippa Ehrlich Context triple: [My Octopus Teacher, director, Pippa Ehrlich]
-
A.
Jennifer Mordaunt
Jennifer Mordaunt is a relative of British Conservative politician Penny Mordaunt.
-
B.
Tanya Chesham-Leigh
Tanya Chesham-Leigh is a fictional character from the "Mamma Mia!" musical and film series, known as one of Donna Sheridan’s glamorous and fun-loving best friends.
-
C.
Philippa Giles
Philippa Giles is a British television producer best known for her work on acclaimed drama series such as Luther.
-
D.
Gillian Siddall
Gillian Siddall is a Canadian academic and university administrator who serves as president of Lakehead University.
-
E.
Alison Telfer
Alison Telfer is a British academic and editor best known as the longtime partner and former wife of Monty Python member Terry Jones.
- 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: Pippa Ehrlich Triple: [My Octopus Teacher, director, Pippa Ehrlich]
Generated description
Pippa Ehrlich is a South African filmmaker and environmental journalist best known for co-directing the Oscar-winning nature documentary "My Octopus Teacher."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Pippa Ehrlich Target entity description: Pippa Ehrlich is a South African filmmaker and environmental journalist best known for co-directing the Oscar-winning nature documentary "My Octopus Teacher."
-
A.
Jennifer Mordaunt
Jennifer Mordaunt is a relative of British Conservative politician Penny Mordaunt.
-
B.
Tanya Chesham-Leigh
Tanya Chesham-Leigh is a fictional character from the "Mamma Mia!" musical and film series, known as one of Donna Sheridan’s glamorous and fun-loving best friends.
-
C.
Philippa Giles
Philippa Giles is a British television producer best known for her work on acclaimed drama series such as Luther.
-
D.
Gillian Siddall
Gillian Siddall is a Canadian academic and university administrator who serves as president of Lakehead University.
-
E.
Alison Telfer
Alison Telfer is a British academic and editor best known as the longtime partner and former wife of Monty Python member Terry Jones.
- 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_69ad8b14ffe881908ffed62f9595c867 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad996fa4388190abd319c69ee583d9 |
completed | March 8, 2026, 3:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b1eede693c8190a49be9d267bed6fa |
completed | March 11, 2026, 10:38 p.m. |
| NEDg | Description generation | batch_69b1ef97b8a88190b5d6c526c32d1b31 |
completed | March 11, 2026, 10:41 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b1f0df33808190900b0422a8057bfd |
completed | March 11, 2026, 10:46 p.m. |
Created at: March 8, 2026, 2:58 p.m.