Triple
T6742498
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mark Stevens |
E154119
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object |
Time Table
Time Table is a crime film noir written by Mark Stevens, who also directed and starred in the movie.
|
E614815
|
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: Time Table | Statement: [Mark Stevens, notableWork, Time Table]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Time Table Context triple: [Mark Stevens, notableWork, Time Table]
-
A.
RTC Transit
RTC Transit is the public bus system serving the Las Vegas Valley in Nevada, providing transportation to major destinations including Allegiant Stadium.
-
B.
Onrail
Onrail is a Norwegian company that operates freight train services on the national railway network.
-
C.
MetroAccess
MetroAccess is a paratransit service providing door-to-door transportation for people with disabilities in the Washington, D.C. metropolitan area.
-
D.
Cloudflare Magic Transit
Cloudflare Magic Transit is a network security and performance service that protects and accelerates on-premise and hybrid network infrastructure by routing traffic through Cloudflare’s global Anycast network.
-
E.
OurTime
OurTime is an online dating platform specifically designed to help singles over 50 connect for relationships and companionship.
- 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: Time Table Triple: [Mark Stevens, notableWork, Time Table]
Generated description
Time Table is a crime film noir written by Mark Stevens, who also directed and starred in the movie.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Time Table Target entity description: Time Table is a crime film noir written by Mark Stevens, who also directed and starred in the movie.
-
A.
RTC Transit
RTC Transit is the public bus system serving the Las Vegas Valley in Nevada, providing transportation to major destinations including Allegiant Stadium.
-
B.
Onrail
Onrail is a Norwegian company that operates freight train services on the national railway network.
-
C.
MetroAccess
MetroAccess is a paratransit service providing door-to-door transportation for people with disabilities in the Washington, D.C. metropolitan area.
-
D.
Cloudflare Magic Transit
Cloudflare Magic Transit is a network security and performance service that protects and accelerates on-premise and hybrid network infrastructure by routing traffic through Cloudflare’s global Anycast network.
-
E.
OurTime
OurTime is an online dating platform specifically designed to help singles over 50 connect for relationships and companionship.
- 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_69c6880d84d8819095d19de2295f26ac |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d1b245988190a9d5260f4872bbea |
completed | March 27, 2026, 6:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c70b11b828819084d5a21dde5f1f5b |
completed | March 27, 2026, 10:56 p.m. |
| NEDg | Description generation | batch_69c70bb0714c819094e80a2dfc960c99 |
completed | March 27, 2026, 10:58 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c70c531c48819086adab0c08f64439 |
completed | March 27, 2026, 11:01 p.m. |
Created at: March 27, 2026, 2:10 p.m.