Triple

T899328
Position Surface form Disambiguated ID Type / Status
Subject Book of Judges E19411 entity
Predicate featuresCharacter P626 FINISHED
Object Deborah
Deborah is a prominent biblical prophetess and judge of Israel known for her leadership and role in delivering the Israelites from Canaanite oppression.
E109288 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: Deborah | Statement: [Book of Judges, featuresCharacter, Deborah]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Deborah
Context triple: [Book of Judges, featuresCharacter, Deborah]
  • A. Miriam
    Miriam is a prominent biblical figure known as the sister of Moses and Aaron and as a prophetess during the Exodus of the Israelites from Egypt.
  • B. Miryam
    Miryam is the Hebrew form of the name of the Virgin Mary, the mother of Jesus in Christian tradition.
  • C. Susanna
    Susanna is a deuterocanonical addition to the Book of Daniel, telling the story of a virtuous woman falsely accused of adultery and vindicated by the prophet Daniel.
  • D. Tessie
    Tessie is a Boston Red Sox mascot character, often depicted as a green monster and associated with Wally the Green Monster.
  • E. Ruth
    Ruth is a supporting character in the comedy Western film "A Million Ways to Die in the West," known for being a devout Christian prostitute engaged to the protagonist's best friend.
  • 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: Deborah
Triple: [Book of Judges, featuresCharacter, Deborah]
Generated description
Deborah is a prominent biblical prophetess and judge of Israel known for her leadership and role in delivering the Israelites from Canaanite oppression.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Deborah
Target entity description: Deborah is a prominent biblical prophetess and judge of Israel known for her leadership and role in delivering the Israelites from Canaanite oppression.
  • A. Miriam
    Miriam is a prominent biblical figure known as the sister of Moses and Aaron and as a prophetess during the Exodus of the Israelites from Egypt.
  • B. Miryam
    Miryam is the Hebrew form of the name of the Virgin Mary, the mother of Jesus in Christian tradition.
  • C. Susanna
    Susanna is a deuterocanonical addition to the Book of Daniel, telling the story of a virtuous woman falsely accused of adultery and vindicated by the prophet Daniel.
  • D. Tessie
    Tessie is a Boston Red Sox mascot character, often depicted as a green monster and associated with Wally the Green Monster.
  • E. Ruth
    Ruth is the given name of Ruth Bader Ginsburg, the pioneering U.S. Supreme Court Justice and prominent advocate for gender equality and civil rights.
  • 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_69a4939e889c8190ac148b3ac1a7f90b completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4ad4162848190aa2787b2fa3e6575 completed March 1, 2026, 9:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7ee02a21c819088e6a137ea306efd completed March 4, 2026, 8:32 a.m.
NEDg Description generation batch_69a7eebc724c8190a364782ec8e672e0 completed March 4, 2026, 8:35 a.m.
NED2 Entity disambiguation (via description) batch_69a7ef2ed2c881909dc1d2d6fb39805a completed March 4, 2026, 8:37 a.m.
Created at: March 1, 2026, 7:39 p.m.