Triple

T26138147
Position Surface form Disambiguated ID Type / Status
Subject تماثيل رمسيس الثاني E659436 entity
Predicate تعود_إلى P159988 FINISHED
Object الأسرة التاسعة عشرة المصرية
الأسرة التاسعة عشرة المصرية هي سلالة من الدولة الحديثة في مصر القديمة اشتهرت بقوتها العسكرية واتساع نفوذها وبحكم ملوك بارزين مثل رمسيس الثاني.
 E1711123 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: الأسرة التاسعة عشرة المصرية | Statement: [تماثيل رمسيس الثاني, تعود_إلى, الأسرة التاسعة عشرة المصرية]
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: الأسرة التاسعة عشرة المصرية
Triple: [تماثيل رمسيس الثاني, تعود_إلى, الأسرة التاسعة عشرة المصرية]
Generated description
الأسرة التاسعة عشرة المصرية هي سلالة من الدولة الحديثة في مصر القديمة اشتهرت بقوتها العسكرية واتساع نفوذها وبحكم ملوك بارزين مثل رمسيس الثاني.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: تعود_إلى
Context triple: [تماثيل رمسيس الثاني, تعود_إلى, الأسرة التاسعة عشرة المصرية]
  • A. تعود_إلى chosen
    Indicates that something or someone returns, goes back, or is attributed back to a previous place, state, source, or reference.
  • B. returnsTo
    Indicates that an entity goes back to a previous location, state, or entity it was associated with before.
  • C. returnToRomeTo
    Indicates that an entity goes back or returns to the location Rome.
  • D. returnedToTour
    Indicates that an entity resumed or went back to participating in a tour after having left or paused it.
  • E. returnedFrom
    Indicates that an entity has come back or been sent back from a specified source, location, or prior state.
  • F. None of above.

Provenance (6 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_69ee5bc3c20c8190bf2cf272f4170e95 completed April 26, 2026, 6:38 p.m.
NER Named-entity recognition batch_69f60be1d2408190820365bf7d8436bd completed May 2, 2026, 2:36 p.m.
NED1 Entity disambiguation (via context triple) batch_6a1127667a6c8190a8ff5bc95fdedad3 completed May 23, 2026, 4:04 a.m.
NEDg Description generation batch_6a114b4c88dc81909e4c49446d1394d0 completed May 23, 2026, 6:38 a.m.
NED2 Entity disambiguation (via description) batch_6a114bae57248190ab262e9736dd2f61 completed May 23, 2026, 6:39 a.m.
PD Predicate disambiguation batch_69f5f7fd90fc81909055b211368f9139 completed May 2, 2026, 1:11 p.m.
Created at: April 26, 2026, 8:18 p.m.