Triple
T9341260
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Crichton |
E224766
|
entity |
| Predicate | directorOf |
P537
|
FINISHED |
| Object |
Coma
Coma is a 1978 medical thriller film, based on Robin Cook’s novel, that explores a sinister conspiracy involving patients mysteriously falling into comas in a Boston hospital.
|
E792709
|
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: Coma | Statement: [Michael Crichton, directorOf, Coma]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Coma Context triple: [Michael Crichton, directorOf, Coma]
-
A.
Coma
"Coma" is a lengthy, hard rock track by Guns N' Roses known for its complex structure, dark themes, and climactic intensity.
-
B.
Cooma
Cooma is a town in New South Wales, Australia, known as a gateway to the Snowy Mountains and the Snowy Mountains Scheme.
-
C.
Comas
Comas is a populous urban district in northern Lima, Peru, known for its residential neighborhoods and commercial activity within the Greater Lima metropolitan area.
-
D.
Coma Pedrosa
Coma Pedrosa is the tallest mountain in Andorra, known for its rugged alpine terrain and popular hiking routes.
-
E.
Biathanatos
Biathanatos is a controversial prose work by John Donne that offers an unusual and paradoxical theological defense of suicide.
- 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: Coma Triple: [Michael Crichton, directorOf, Coma]
Generated description
Coma is a 1978 medical thriller film, based on Robin Cook’s novel, that explores a sinister conspiracy involving patients mysteriously falling into comas in a Boston hospital.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Coma Target entity description: Coma is a 1978 medical thriller film, based on Robin Cook’s novel, that explores a sinister conspiracy involving patients mysteriously falling into comas in a Boston hospital.
-
A.
Coma
"Coma" is a lengthy, hard rock track by Guns N' Roses known for its complex structure, dark themes, and climactic intensity.
-
B.
Cooma
Cooma is a town in New South Wales, Australia, known as a gateway to the Snowy Mountains and the Snowy Mountains Scheme.
-
C.
Comas
Comas is a populous urban district in northern Lima, Peru, known for its residential neighborhoods and commercial activity within the Greater Lima metropolitan area.
-
D.
Coma Pedrosa
Coma Pedrosa is the tallest mountain in Andorra, known for its rugged alpine terrain and popular hiking routes.
-
E.
Biathanatos
Biathanatos is a controversial prose work by John Donne that offers an unusual and paradoxical theological defense of suicide.
- 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_69ca84286fcc81909f6e7fd7a7e862a2 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd4bafa9108190889397614756020d |
completed | April 1, 2026, 4:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0e3f94ab88190a4c5a9129bd2ca14 |
completed | April 4, 2026, 10:12 a.m. |
| NEDg | Description generation | batch_69d0e573af788190be4baaa3afb87ca2 |
completed | April 4, 2026, 10:18 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d0e607944c81909a421828595cd793 |
completed | April 4, 2026, 10:20 a.m. |
Created at: March 30, 2026, 7:40 p.m.