Triple

T16009739
Position Surface form Disambiguated ID Type / Status
Subject Mary Malone E388306 entity
Predicate associatedWith P37 FINISHED
Object the Mulefa
The Mulefa are a fictional species from Philip Pullman’s His Dark Materials universe, known for their diamond-framed bodies, use of seed-pod wheels, and deep, symbiotic connection to the substance called Dust.
E1189669 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: the Mulefa | Statement: [Mary Malone, associatedWith, the Mulefa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: the Mulefa
Context triple: [Mary Malone, associatedWith, the Mulefa]
  • A. Mulee'aage
    Mulee'aage is the official presidential palace and primary residence of the President of the Maldives, located in the capital city Malé.
  • B. Mungava
    Mungava is an alternative name for Bellona Island, a small inhabited island in the Solomon Islands in the South Pacific.
  • C. Mugatu
    Mugatu is the flamboyant, villainous fashion designer portrayed by Will Ferrell in the comedy film "Zoolander."
  • D. Mwaghavul
    Mwaghavul is a Chadic language spoken primarily by the Mwaghavul people in Plateau State, central Nigeria.
  • E. Mungaka
    Mungaka is a Grassfields Bantu language spoken primarily in Cameroon, particularly associated with the Bamunka (Ndop) area.
  • 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: the Mulefa
Triple: [Mary Malone, associatedWith, the Mulefa]
Generated description
The Mulefa are a fictional species from Philip Pullman’s His Dark Materials universe, known for their diamond-framed bodies, use of seed-pod wheels, and deep, symbiotic connection to the substance called Dust.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: the Mulefa
Target entity description: The Mulefa are a fictional species from Philip Pullman’s His Dark Materials universe, known for their diamond-framed bodies, use of seed-pod wheels, and deep, symbiotic connection to the substance called Dust.
  • A. Mulee'aage
    Mulee'aage is the official presidential palace and primary residence of the President of the Maldives, located in the capital city Malé.
  • B. Mungava
    Mungava is an alternative name for Bellona Island, a small inhabited island in the Solomon Islands in the South Pacific.
  • C. Mugatu
    Mugatu is the flamboyant, villainous fashion designer portrayed by Will Ferrell in the comedy film "Zoolander."
  • D. Mwaghavul
    Mwaghavul is a Chadic language spoken primarily by the Mwaghavul people in Plateau State, central Nigeria.
  • E. Mungaka
    Mungaka is a Grassfields Bantu language spoken primarily in Cameroon, particularly associated with the Bamunka (Ndop) area.
  • 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_69d86dabcb7c8190b6a39d6831d2fa1b completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1828f8c688190a6b365f9140cd2d8 completed April 17, 2026, 12:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffcf24a9d8819083d7b11d71442da6 completed May 10, 2026, 12:19 a.m.
NEDg Description generation batch_69ffd065cb948190b0ad7e89a12ce535 completed May 10, 2026, 12:25 a.m.
NED2 Entity disambiguation (via description) batch_69ffd1a52de08190a7b283af83be1f42 completed May 10, 2026, 12:30 a.m.
Created at: April 10, 2026, 4:55 a.m.