Triple
T5532812
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Texas Chainsaw 3D |
E145088
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object |
Debra Sullivan
Debra Sullivan is a screenwriter best known for co-writing the horror film "Texas Chainsaw 3D."
|
E691544
|
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: Debra Sullivan | Statement: [Texas Chainsaw 3D, screenwriter, Debra Sullivan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Debra Sullivan Context triple: [Texas Chainsaw 3D, screenwriter, Debra Sullivan]
-
A.
Debra Humphries
Debra Humphries is the mother of former NBA player Kris Humphries.
-
B.
Deborah Dudley
Deborah Dudley was a daughter of Thomas Dudley, the colonial governor of Massachusetts Bay Colony, and a member of his prominent Puritan family in early New England.
-
C.
Tricia Sullivan
Tricia Sullivan is an American-born science fiction author known for her innovative, genre-bending novels and award-winning contributions to speculative fiction.
-
D.
Deanna Oliver
Deanna Oliver is an American screenwriter and voice actress best known for co-writing the 1995 live-action/CGI family film "Casper."
-
E.
Deborah Prentice
Deborah Prentice is an American social psychologist and academic leader known for her work on social norms and for serving as Vice-Chancellor of the University of Cambridge.
- 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: Debra Sullivan Triple: [Texas Chainsaw 3D, screenwriter, Debra Sullivan]
Generated description
Debra Sullivan is a screenwriter best known for co-writing the horror film "Texas Chainsaw 3D."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Debra Sullivan Target entity description: Debra Sullivan is a screenwriter best known for co-writing the horror film "Texas Chainsaw 3D."
-
A.
Debra Humphries
Debra Humphries is the mother of former NBA player Kris Humphries.
-
B.
Deborah Dudley
Deborah Dudley was a daughter of Thomas Dudley, the colonial governor of Massachusetts Bay Colony, and a member of his prominent Puritan family in early New England.
-
C.
Tricia Sullivan
Tricia Sullivan is an American-born science fiction author known for her innovative, genre-bending novels and award-winning contributions to speculative fiction.
-
D.
Deanna Oliver
Deanna Oliver is an American screenwriter and voice actress best known for co-writing the 1995 live-action/CGI family film "Casper."
-
E.
Deborah Prentice
Deborah Prentice is an American social psychologist and academic leader known for her work on social norms and for serving as Vice-Chancellor of the University of Cambridge.
- 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_69c008f9955881909bfa8348b56b4739 |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c01f9ea2c88190a68642f5799bd8ff |
completed | March 22, 2026, 4:58 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c98f54f0908190afec4f26e96d8173 |
completed | March 29, 2026, 8:45 p.m. |
| NEDg | Description generation | batch_69c990477ec881909ba48e92ec8ef64f |
completed | March 29, 2026, 8:49 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c9909f9fac81909a15f09cbb654524 |
completed | March 29, 2026, 8:50 p.m. |
Created at: March 22, 2026, 3:34 p.m.