Triple
T9578550
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Training Day (TV series) |
E231109
|
entity |
| Predicate | alsoStarring |
P14987
|
FINISHED |
| Object |
Katrina Law
Katrina Law is an American actress known for her roles in television series such as Spartacus, Arrow, and Hawaii Five-0.
|
E809292
|
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: Katrina Law | Statement: [Training Day (TV series), alsoStarring, Katrina Law]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Katrina Law Context triple: [Training Day (TV series), alsoStarring, Katrina Law]
-
A.
Katrina Greenwood
Katrina Greenwood is known as the long-term partner of acclaimed Australian actor Hugo Weaving.
-
B.
Katrina Bennett
Katrina Bennett is a sharp, ambitious corporate lawyer in the TV series "Suits," known for her meticulous work ethic and evolving loyalty within the firm.
-
C.
Kyla Deaver
Kyla Deaver is an American child actress best known for her role in the horror film "The Conjuring."
-
D.
Katrina Johnson
Katrina Johnson is an American actress and comedian best known for being an original cast member on the Nickelodeon sketch comedy series "All That" in the 1990s.
-
E.
Julie Anne Legate
Julie Anne Legate is a linguist known for her work in theoretical syntax and morphosyntax, and a professor in the Department of Linguistics at the University of Pennsylvania.
- 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: Katrina Law Triple: [Training Day (TV series), alsoStarring, Katrina Law]
Generated description
Katrina Law is an American actress known for her roles in television series such as Spartacus, Arrow, and Hawaii Five-0.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Katrina Law Target entity description: Katrina Law is an American actress known for her roles in television series such as Spartacus, Arrow, and Hawaii Five-0.
-
A.
Katrina Greenwood
Katrina Greenwood is known as the long-term partner of acclaimed Australian actor Hugo Weaving.
-
B.
Katrina Bennett
Katrina Bennett is a sharp, ambitious corporate lawyer in the TV series "Suits," known for her meticulous work ethic and evolving loyalty within the firm.
-
C.
Kyla Deaver
Kyla Deaver is an American child actress best known for her role in the horror film "The Conjuring."
-
D.
Katrina Johnson
Katrina Johnson is an American actress and comedian best known for being an original cast member on the Nickelodeon sketch comedy series "All That" in the 1990s.
-
E.
Julie Anne Legate
Julie Anne Legate is a linguist known for her work in theoretical syntax and morphosyntax, and a professor in the Department of Linguistics at the University of Pennsylvania.
- 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_69ca848091c48190bc313d6620d09555 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd99aece1081908287e03106de020f |
completed | April 1, 2026, 10:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1615d093c8190940037e9e0842db5 |
completed | April 4, 2026, 7:07 p.m. |
| NEDg | Description generation | batch_69d161e6a1308190932c8386e1c24f2e |
completed | April 4, 2026, 7:09 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d165a8c80081909e4d0837cbaabf95 |
completed | April 4, 2026, 7:25 p.m. |
Created at: March 30, 2026, 8:05 p.m.