Triple
T5043390
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arrow in the Dust |
E113599
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object |
Keith Larsen
Keith Larsen was an American actor best known for his roles in 1950s Western films and television series.
|
E490177
|
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: Keith Larsen | Statement: [Arrow in the Dust, starring, Keith Larsen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Keith Larsen Context triple: [Arrow in the Dust, starring, Keith Larsen]
-
A.
Michael Larsen
Michael Larsen is the person credited with coining the now-popular term “Painted Ladies” to describe the colorfully restored Victorian and Edwardian houses of San Francisco.
-
B.
Dean Paul Larson
Dean Paul Larson is a fictional character from the television series "The Chair."
-
C.
Kurt Johnstad
Kurt Johnstad is an American screenwriter best known for writing the action films "300" and "Atomic Blonde."
-
D.
Warren Skaaren
Warren Skaaren was an American screenwriter and script doctor best known for his work on major 1980s films such as "Beetlejuice" and "Batman."
-
E.
Lars Heikensten
Lars Heikensten is a Swedish economist and former Governor of Sveriges Riksbank who has also held prominent roles in European financial institutions and cultural organizations.
- 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: Keith Larsen Triple: [Arrow in the Dust, starring, Keith Larsen]
Generated description
Keith Larsen was an American actor best known for his roles in 1950s Western films and television series.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Keith Larsen Target entity description: Keith Larsen was an American actor best known for his roles in 1950s Western films and television series.
-
A.
Michael Larsen
Michael Larsen is the person credited with coining the now-popular term “Painted Ladies” to describe the colorfully restored Victorian and Edwardian houses of San Francisco.
-
B.
Dean Paul Larson
Dean Paul Larson is a fictional character from the television series "The Chair."
-
C.
Kurt Johnstad
Kurt Johnstad is an American screenwriter best known for writing the action films "300" and "Atomic Blonde."
-
D.
Warren Skaaren
Warren Skaaren was an American screenwriter and script doctor best known for his work on major 1980s films such as "Beetlejuice" and "Batman."
-
E.
Lars Heikensten
Lars Heikensten is a Swedish economist and former Governor of Sveriges Riksbank who has also held prominent roles in European financial institutions and cultural organizations.
- 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_69bd44391fc48190a311ce9c826c209b |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd73fc04f08190aba851fa0192d0fb |
completed | March 20, 2026, 4:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bea47c5f808190821d7f708003a07d |
completed | March 21, 2026, 2 p.m. |
| NEDg | Description generation | batch_69bea509ff4c8190be2ce24e84366ea8 |
completed | March 21, 2026, 2:02 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69bea577f4b0819084d579e4d4804947 |
completed | March 21, 2026, 2:04 p.m. |
Created at: March 20, 2026, 1:37 p.m.