Triple
T12604962
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Network |
E300953
|
entity |
| Predicate | character |
P662
|
FINISHED |
| Object |
Diana Christensen
Diana Christensen is the ambitious, coldly calculating television executive and central antagonist in the 1976 satirical film "Network."
|
E1001490
|
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: Diana Christensen | Statement: [Network, character, Diana Christensen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Diana Christensen Context triple: [Network, character, Diana Christensen]
-
A.
Tina Christensen
Tina Christensen is a Danish film editor and translator known for her work subtitling and editing a wide range of international films.
-
B.
Christine Olsen
Christine Olsen is an Australian film producer best known for her work on the acclaimed drama "Rabbit-Proof Fence."
-
C.
Susan Christensen
Susan Christensen is an American jurist who serves as the Chief Justice of the Iowa Supreme Court.
-
D.
Diana Parker
Diana Parker is a character in Jane Austen’s unfinished novel "Sanditon," depicted as one of the hypochondriacal Parker siblings involved in promoting the seaside resort.
-
E.
Christine Lund
Christine Lund is known as the spouse of Pulitzer Prize–winning American editorial cartoonist Bill Mauldin.
- 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: Diana Christensen Triple: [Network, character, Diana Christensen]
Generated description
Diana Christensen is the ambitious, coldly calculating television executive and central antagonist in the 1976 satirical film "Network."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Diana Christensen Target entity description: Diana Christensen is the ambitious, coldly calculating television executive and central antagonist in the 1976 satirical film "Network."
-
A.
Tina Christensen
Tina Christensen is a Danish film editor and translator known for her work subtitling and editing a wide range of international films.
-
B.
Christine Olsen
Christine Olsen is an Australian film producer best known for her work on the acclaimed drama "Rabbit-Proof Fence."
-
C.
Susan Christensen
Susan Christensen is an American jurist who serves as the Chief Justice of the Iowa Supreme Court.
-
D.
Diana Parker
Diana Parker is a character in Jane Austen’s unfinished novel "Sanditon," depicted as one of the hypochondriacal Parker siblings involved in promoting the seaside resort.
-
E.
Christine Lund
Christine Lund is known as the spouse of Pulitzer Prize–winning American editorial cartoonist Bill Mauldin.
- 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_69d7bdea2ca881908f379526c13b1145 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d954e7f2dc8190a42cab7a0e5ea7f3 |
completed | April 10, 2026, 7:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f684daedc88190adc403f27a850b7a |
completed | May 2, 2026, 11:12 p.m. |
| NEDg | Description generation | batch_69f685dac5cc8190b4bc2d81186c9266 |
completed | May 2, 2026, 11:16 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f6869156048190b548ecd04561deb8 |
completed | May 2, 2026, 11:19 p.m. |
Created at: April 9, 2026, 5:10 p.m.