Triple
T11726571
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Patricia Cornwell |
E278785
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object |
Trace
"Trace" is a crime novel by Patricia Cornwell featuring medical examiner Dr. Kay Scarpetta as she investigates a complex and disturbing case.
|
E943058
|
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: Trace | Statement: [Patricia Cornwell, notableWork, Trace]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Trace Context triple: [Patricia Cornwell, notableWork, Trace]
-
A.
Trace
Trace is a large-scale installation by Chinese artist Ai Weiwei composed of thousands of LEGO portraits depicting political prisoners and activists from around the world.
-
B.
TRACE
TRACE is a U.S. Financial Industry Regulatory Authority (FINRA) system that provides real-time public reporting and transparency for over-the-counter corporate bond and other fixed-income securities transactions.
-
C.
Traces
Traces is a song co-written and produced by American songwriter and producer Buddy Buie, best known through its hit recording by the Classics IV.
-
D.
Traces
Traces is a work by American historian and author James B. Cobb Jr., likely exploring themes related to the history and culture of the American South.
-
E.
Traces
Traces is a film featuring British actor Vincent Regan in a prominent role.
- 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: Trace Triple: [Patricia Cornwell, notableWork, Trace]
Generated description
"Trace" is a crime novel by Patricia Cornwell featuring medical examiner Dr. Kay Scarpetta as she investigates a complex and disturbing case.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Trace Target entity description: "Trace" is a crime novel by Patricia Cornwell featuring medical examiner Dr. Kay Scarpetta as she investigates a complex and disturbing case.
-
A.
Trace
Trace is a large-scale installation by Chinese artist Ai Weiwei composed of thousands of LEGO portraits depicting political prisoners and activists from around the world.
-
B.
TRACE
TRACE is a U.S. Financial Industry Regulatory Authority (FINRA) system that provides real-time public reporting and transparency for over-the-counter corporate bond and other fixed-income securities transactions.
-
C.
Traces
Traces is a song co-written and produced by American songwriter and producer Buddy Buie, best known through its hit recording by the Classics IV.
-
D.
Traces
Traces is a work by American historian and author James B. Cobb Jr., likely exploring themes related to the history and culture of the American South.
-
E.
Traces
Traces is a film featuring British actor Vincent Regan in a prominent role.
- 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_69d6aaffec6881908bead509e8621742 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a4d70d908190b5f47c2ef501a191 |
completed | April 10, 2026, 7:20 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ef83e9efdc8190830f9b9cb5362b1c |
completed | April 27, 2026, 3:42 p.m. |
| NEDg | Description generation | batch_69ef96b13be881908102ffa867f96c22 |
completed | April 27, 2026, 5:02 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69efb51113708190998b570c33b9d0e7 |
completed | April 27, 2026, 7:12 p.m. |
Created at: April 8, 2026, 9:41 p.m.