Triple

T5380791
Position Surface form Disambiguated ID Type / Status
Subject Richard Donner E113075 entity
Predicate directed P7373 FINISHED
Object Timeline
"Timeline" is a 2003 science fiction adventure film based on Michael Crichton's novel, involving archaeologists who travel back to medieval France using experimental time-travel technology.
 E515424 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: Timeline | Statement: [Richard Donner, directed, Timeline]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Timeline
Context triple: [Richard Donner, directed, Timeline]
  • A. Time
    Time is a major American news magazine known for its influential coverage of current events, politics, and culture.
  • B. Time
    Time is a 1995 song by the American rock band Screaming Trees, featured on their album "Dust."
  • C. Time
    Time is a personified embodiment of time itself, portrayed as an eccentric, clockwork-like being in the fantasy film "Alice Through the Looking Glass."
  • D. Time
    "Time" is a 1981 concept album by Electric Light Orchestra that blends rock and synth-pop in a futuristic, time-travel-themed narrative.
  • E. Time
    "Time" is a novel by Stephen Graham that explores themes of temporality and human experience through reflective, often philosophical prose.
  • 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: Timeline
Triple: [Richard Donner, directed, Timeline]
Generated description
"Timeline" is a 2003 science fiction adventure film based on Michael Crichton's novel, involving archaeologists who travel back to medieval France using experimental time-travel technology.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Timeline
Target entity description: "Timeline" is a 2003 science fiction adventure film based on Michael Crichton's novel, involving archaeologists who travel back to medieval France using experimental time-travel technology.
  • A. Time
    Time is a major American news magazine known for its influential coverage of current events, politics, and culture.
  • B. Time
    Time is a 1995 song by the American rock band Screaming Trees, featured on their album "Dust."
  • C. Time
    Time is a personified embodiment of time itself, portrayed as an eccentric, clockwork-like being in the fantasy film "Alice Through the Looking Glass."
  • D. Time
    "Time" is a 1981 concept album by Electric Light Orchestra that blends rock and synth-pop in a futuristic, time-travel-themed narrative.
  • E. Time
    "Time" is a novel by Stephen Graham that explores themes of temporality and human experience through reflective, often philosophical prose.
  • 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_69bd4436a1988190af18dcff7fd306b4 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd86cfe7fc8190bb73c60cae7c927d completed March 20, 2026, 5:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf2949cd9881908ca0d8fdf1642f71 completed March 21, 2026, 11:27 p.m.
NEDg Description generation batch_69bf2a46c4808190bd706cbb76bbfbc2 completed March 21, 2026, 11:31 p.m.
NED2 Entity disambiguation (via description) batch_69bf2ab19a50819098ef5a611daa8cd6 completed March 21, 2026, 11:33 p.m.
Created at: March 20, 2026, 2:03 p.m.