Triple

T405040
Position Surface form Disambiguated ID Type / Status
Subject Abraham E9364 entity
Predicate spouse P13 FINISHED
Object Keturah
Keturah is a woman in the Hebrew Bible known as a later wife or concubine of Abraham, through whom several Arabian tribes are traditionally traced.
 E51875 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: Keturah | Statement: [Abraham, spouse, Keturah]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Keturah
Context triple: [Abraham, spouse, Keturah]
  • A. Hagar
    Hagar is a biblical figure known as the Egyptian servant of Sarah who bore Abraham’s son Ishmael and is revered in Jewish, Christian, and Islamic traditions.
  • B. Miryam
    Miryam is the Hebrew form of the name of the Virgin Mary, the mother of Jesus in Christian tradition.
  • C. Rebekah
    Rebekah is a feminine given name, traditionally associated with the biblical matriarch Rebecca and used in various English-speaking cultures.
  • D. Hanan
    Hanan is a given name most notably borne by Palestinian legislator, activist, and scholar Hanan Ashrawi.
  • E. Haggith
    Haggith is a lesser-known wife of King David in the Hebrew Bible and the mother of his son Adonijah.
  • 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: Keturah
Triple: [Abraham, spouse, Keturah]
Generated description
Keturah is a woman in the Hebrew Bible known as a later wife or concubine of Abraham, through whom several Arabian tribes are traditionally traced.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Keturah
Target entity description: Keturah is a woman in the Hebrew Bible known as a later wife or concubine of Abraham, through whom several Arabian tribes are traditionally traced.
  • A. Hagar
    Hagar is a biblical figure known as the Egyptian servant of Sarah who bore Abraham’s son Ishmael and is revered in Jewish, Christian, and Islamic traditions.
  • B. Miryam
    Miryam is the Hebrew form of the name of the Virgin Mary, the mother of Jesus in Christian tradition.
  • C. Rebekah
    Rebekah is a feminine given name, traditionally associated with the biblical matriarch Rebecca and used in various English-speaking cultures.
  • D. Hanan
    Hanan is a given name most notably borne by Palestinian legislator, activist, and scholar Hanan Ashrawi.
  • E. Haggith
    Haggith is a lesser-known wife of King David in the Hebrew Bible and the mother of his son Adonijah.
  • 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_69a2e8004cb88190b92ed1add6abf41a completed Feb. 28, 2026, 1:05 p.m.
NER Named-entity recognition batch_69a2eca37fe881909802126952dfdd59 completed Feb. 28, 2026, 1:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69a41774cd008190a254facf9cba90b6 completed March 1, 2026, 10:39 a.m.
NEDg Description generation batch_69a418da55088190935babe9abae5ac4 completed March 1, 2026, 10:45 a.m.
NED2 Entity disambiguation (via description) batch_69a4196334948190a1f6004b1a292550 completed March 1, 2026, 10:48 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.