Triple

T23486842
Position Surface form Disambiguated ID Type / Status
Subject Polly Holliday E570555 entity
Predicate televisionSeries P3279 FINISHED
Object Alice
"Alice" is an American sitcom that aired from the mid-1970s to the mid-1980s, following a widowed waitress and her coworkers at a roadside diner.
E136578 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: Alice | Statement: [Polly Holliday, televisionSeries, Alice]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Alice
Context triple: [Polly Holliday, televisionSeries, Alice]
  • A. Alice
    Alice is the curious young girl who serves as the main protagonist of Disney’s animated film "Alice in Wonderland."
  • B. Alice
    Alice is a Direct Memory Access (DMA) controller used in Commodore's Amiga AGA chipset generation to handle high-speed data transfers between memory and peripherals.
  • C. Alice
    "Alice" is a song featured on Avril Lavigne’s album *Goodbye Lullaby*, known for its emotive, piano-driven rock style and connection to the film *Alice in Wonderland*.
  • D. Alice
    Alice is the protagonist of the film "Race with the Devil," around whom the story’s suspenseful and perilous events revolve.
  • E. Alice
    Alice is an ultraviolet imaging spectrograph aboard NASA's New Horizons spacecraft, used to study the composition and structure of planetary atmospheres and surfaces.
  • 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: Alice
Triple: [Polly Holliday, televisionSeries, Alice]
Generated description
"Alice" is an American sitcom that aired from the mid-1970s to the mid-1980s, following a widowed waitress and her coworkers at a roadside diner.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Alice
Target entity description: "Alice" is an American sitcom that aired from the mid-1970s to the mid-1980s, following a widowed waitress and her coworkers at a roadside diner.
  • A. Alice chosen
    Alice is an American sitcom that aired from the mid-1970s to the mid-1980s, following a widowed waitress working at a roadside diner and the quirky people in her life.
  • B. Alice
    "Alice" is a 1988 American comedy-drama film featuring Celia Weston in a notable role.
  • C. Alice
    Alice is a central comedic character in the film "Mike and Dave Need Wedding Dates," known for her wild, unpredictable behavior as one of the women who answer the brothers’ ad for wedding dates.
  • D. Alice
    "Alice" is a 1990 romantic comedy-drama film written and directed by Woody Allen, starring Mia Farrow as a wealthy Manhattan woman undergoing a magical, introspective midlife crisis.
  • E. Alice
    Alice is a recurring engineer character in the "Dilbert" comic strip, known for her technical competence and no-nonsense attitude in a dysfunctional corporate workplace.
  • F. None of above.

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_69e245b0b01481908f636939bedd804c completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a754825481909b005ca5654c3159 completed April 29, 2026, 6:38 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0cdf40b5648190bca1ec5f6e87ba5c completed May 19, 2026, 10:08 p.m.
NEDg Description generation batch_6a0ce451ec9c8190bf31e337e6979238 completed May 19, 2026, 10:29 p.m.
NED2 Entity disambiguation (via description) batch_6a0ce4e165688190a60fdef18dd370fe completed May 19, 2026, 10:32 p.m.
Created at: April 17, 2026, 6:04 p.m.