Triple

T14120133
Position Surface form Disambiguated ID Type / Status
Subject John Darling E339881 entity
Predicate relative P37 FINISHED
Object Nana
Nana is the beloved canine nursemaid in J.M. Barrie’s Peter Pan, who dutifully looks after the Darling children.
E1080563 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: Nana | Statement: [John Darling, relative, Nana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nana
Context triple: [John Darling, relative, Nana]
  • A. Nana
    Nana was a prominent Chiricahua Apache war leader who fought alongside Geronimo in resistance to U.S. and Mexican military forces in the late 19th century.
  • B. Nana
    "Nana" is a popular hit single by Tanzanian Bongo Flava artist Diamond Platnumz, known for its romantic theme and widespread success across East Africa.
  • C. Nana
    Nana is a character in the play "The Visit," serving as part of the story’s supporting cast in Friedrich Dürrenmatt’s darkly comic exploration of justice and revenge.
  • D. Nana
    Nana is a figure in Phrygian mythology, often regarded as the mother of the vegetation god Attis and associated with themes of miraculous birth and fertility.
  • E. Nana
    Nana is a common Akan given name in Ghana, often used as a title of respect and borne by various notable figures including political leaders.
  • 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: Nana
Triple: [John Darling, relative, Nana]
Generated description
Nana is the beloved canine nursemaid in J.M. Barrie’s Peter Pan, who dutifully looks after the Darling children.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Nana
Target entity description: Nana is the beloved canine nursemaid in J.M. Barrie’s Peter Pan, who dutifully looks after the Darling children.
  • A. Nana
    Nana is a character in the play "The Visit," serving as part of the story’s supporting cast in Friedrich Dürrenmatt’s darkly comic exploration of justice and revenge.
  • B. Nana
    Nana is a figure in Phrygian mythology, often regarded as the mother of the vegetation god Attis and associated with themes of miraculous birth and fertility.
  • C. Nana
    Nana is an Indian honorific title commonly used to respectfully address an elder man or grandfather.
  • D. Nana
    Nana is an 1880 naturalist novel by Émile Zola that follows the rise and fall of a Parisian courtesan as a critique of Second Empire society.
  • E. Nana
    Nana is a common Akan given name in Ghana, often used as a title of respect and borne by various notable figures including political leaders.
  • 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_69d81c6a95b481909e39111e0c1f31ee completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de60942a588190beff0058a92f7051 completed April 14, 2026, 3:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcd0bc60088190a7e2f0c9532304e3 completed May 7, 2026, 5:49 p.m.
NEDg Description generation batch_69fcd56da6408190bdbce6581c51d065 completed May 7, 2026, 6:09 p.m.
NED2 Entity disambiguation (via description) batch_69fcd5f8266081909ff9148a77d63ea8 completed May 7, 2026, 6:12 p.m.
Created at: April 9, 2026, 10:22 p.m.