Triple

T1862383
Position Surface form Disambiguated ID Type / Status
Subject Ems E34843 entity
Predicate tributary P415 FINISHED
Object Leda
Leda is a river in northwestern Germany that serves as a significant tributary of the Ems.
 E207309 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: Leda | Statement: [Ems, tributary, Leda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Leda
Context triple: [Ems, tributary, Leda]
  • A. Leda
    Leda is a figure in Greek mythology, a Spartan queen best known as the mother of Helen of Troy and the Dioscuri after being seduced by Zeus.
  • B. Celaeno
    Celaeno is one of the Pleiad nymphs in Greek mythology, a daughter of the Titan Atlas and the Oceanid Pleione.
  • C. Danaë
    Danaë is a princess in Greek mythology, mother of the hero Perseus, famously imprisoned by her father and visited by Zeus in the form of golden rain.
  • D. Helen
    Helen is a figure from Greek mythology famed for her extraordinary beauty, whose abduction by Paris sparked the Trojan War.
  • E. Helen
    Helen is the birth name of Beatrix Potter, the renowned English writer and illustrator best known for her children's books featuring animal characters such as Peter Rabbit.
  • 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: Leda
Triple: [Ems, tributary, Leda]
Generated description
Leda is a river in northwestern Germany that serves as a significant tributary of the Ems.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Leda
Target entity description: Leda is a river in northwestern Germany that serves as a significant tributary of the Ems.
  • A. Leda
    Leda is a figure in Greek mythology, a Spartan queen best known as the mother of Helen of Troy and the Dioscuri after being seduced by Zeus.
  • B. Celaeno
    Celaeno is one of the Pleiad nymphs in Greek mythology, a daughter of the Titan Atlas and the Oceanid Pleione.
  • C. Danaë
    Danaë is a princess in Greek mythology, mother of the hero Perseus, famously imprisoned by her father and visited by Zeus in the form of golden rain.
  • D. Helen
    Helen is the birth name of Beatrix Potter, the renowned English writer and illustrator best known for her children's books featuring animal characters such as Peter Rabbit.
  • E. Helen
    Helen is a figure from Greek mythology famed for her extraordinary beauty, whose abduction by Paris sparked the Trojan War.
  • 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_69a88600b2f88190bc09303e68ab517e completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69abb09e714881909cef0f7e77b5b3b9 completed March 7, 2026, 4:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69add1d026748190a507872de85c908d completed March 8, 2026, 7:45 p.m.
NEDg Description generation batch_69add27390b08190942b1fa6fcab1e44 completed March 8, 2026, 7:48 p.m.
NED2 Entity disambiguation (via description) batch_69add305bd108190b5e7e0f3d30a2c58 completed March 8, 2026, 7:50 p.m.
Created at: March 4, 2026, 7:34 p.m.