Triple

T23889523
Position Surface form Disambiguated ID Type / Status
Subject بنسيون ميرامار E600721 entity
Predicate يملكه_في_الرواية P153951 FINISHED
Object الست ماريانا
الست ماريانا هي صاحبة البنسيون اليونانية العجوز في رواية "ميرامار" لنجيب محفوظ، والتي تمثل محورًا للأحداث وتجمع حولها شخصيات الرواية المختلفة.
 E1610691 NE FINISHED

How this triple was built (3 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: الست ماريانا | Statement: [بنسيون ميرامار, يملكه_في_الرواية, الست ماريانا]
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: الست ماريانا
Triple: [بنسيون ميرامار, يملكه_في_الرواية, الست ماريانا]
Generated description
الست ماريانا هي صاحبة البنسيون اليونانية العجوز في رواية "ميرامار" لنجيب محفوظ، والتي تمثل محورًا للأحداث وتجمع حولها شخصيات الرواية المختلفة.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: يملكه_في_الرواية
Context triple: [بنسيون ميرامار, يملكه_في_الرواية, الست ماريانا]
  • A. guardedByInFiction
    Indicates that one fictional entity is protected or watched over by another within a narrative context.
  • B. literaryWorkInStory
    Indicates that one literary work is referenced, featured, or embedded within the narrative of another story.
  • C. containsBook
    Indicates that one entity (typically a container or collection) includes a specific book as part of its contents.
  • D. عدد الحروف
    Indicates the relationship that specifies the number of letters contained in a given word or text.
  • E. book1Contains
    Indicates that one book includes, encloses, or has as part of its content another specified element or section.
  • F. None of above. chosen

Provenance (7 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_69e295341ac0819080647f2908af793c completed April 17, 2026, 8:16 p.m.
NER Named-entity recognition batch_69f1cd029be48190b9319e59bf5d3a4d completed April 29, 2026, 9:18 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0f7623282481909355c1422de85f3e completed May 21, 2026, 9:16 p.m.
NEDg Description generation batch_6a0f77855e2c81909c3e92f499d134dc completed May 21, 2026, 9:22 p.m.
NED2 Entity disambiguation (via description) batch_6a0f790a4d648190b210725d44601bca completed May 21, 2026, 9:28 p.m.
PD Predicate disambiguation batch_69f1614e24b48190a1c8fb5b7c75ee0f completed April 29, 2026, 1:39 a.m.
PDg Predicate description generation batch_69f167dca3608190ace9d2eef56b2af6 completed April 29, 2026, 2:07 a.m.
Created at: April 17, 2026, 8:25 p.m.