Triple

T6343694
Position Surface form Disambiguated ID Type / Status
Subject Mesha Stele E142692 entity
Predicate mentionsPlace P831 FINISHED
Object Ataroth
Ataroth is an ancient Moabite town known from biblical texts and the Mesha Stele, associated with conflicts between Israel and Moab.
 E585674 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: Ataroth | Statement: [Mesha Stele, mentionsPlace, Ataroth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ataroth
Context triple: [Mesha Stele, mentionsPlace, Ataroth]
  • A. Argobba
    Argobba is an endangered South Semitic language spoken by the Argobba people in central Ethiopia.
  • B. Halistra
    Halistra is a small crofting settlement on the Waternish peninsula of the Isle of Skye in Scotland.
  • C. Tirhuta
    Tirhuta is a historical Brahmic script traditionally used for writing the Maithili language in the Mithila region of India and Nepal.
  • D. Arakhin
    Arakhin is a tractate of the Mishnah and Talmud that deals primarily with the laws of vows of valuation and consecration to the Temple.
  • E. Alatyr
    Alatyr is a historic town in the Chuvash Republic of Russia, known as a regional cultural center with roots dating back to the medieval period.
  • 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: Ataroth
Triple: [Mesha Stele, mentionsPlace, Ataroth]
Generated description
Ataroth is an ancient Moabite town known from biblical texts and the Mesha Stele, associated with conflicts between Israel and Moab.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ataroth
Target entity description: Ataroth is an ancient Moabite town known from biblical texts and the Mesha Stele, associated with conflicts between Israel and Moab.
  • A. Argobba
    Argobba is an endangered South Semitic language spoken by the Argobba people in central Ethiopia.
  • B. Halistra
    Halistra is a small crofting settlement on the Waternish peninsula of the Isle of Skye in Scotland.
  • C. Tirhuta
    Tirhuta is a historical Brahmic script traditionally used for writing the Maithili language in the Mithila region of India and Nepal.
  • D. Arakhin
    Arakhin is a tractate of the Mishnah and Talmud that deals primarily with the laws of vows of valuation and consecration to the Temple.
  • E. Alatyr
    Alatyr is a historic town in the Chuvash Republic of Russia, known as a regional cultural center with roots dating back to the medieval period.
  • 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_69c008d5ab108190b346c465696824a9 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c0674702d08190806ef0998960b797 completed March 22, 2026, 10:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6044051548190bd35bc17b72fab90 completed March 27, 2026, 4:14 a.m.
NEDg Description generation batch_69c6053eb344819094490ad663413962 completed March 27, 2026, 4:19 a.m.
NED2 Entity disambiguation (via description) batch_69c605d48e848190bf11f3862a12d709 completed March 27, 2026, 4:21 a.m.
Created at: March 22, 2026, 4:31 p.m.