Triple

T13625859
Position Surface form Disambiguated ID Type / Status
Subject Shephelah E325578 entity
Predicate containsSite P5003 FINISHED
Object Mareshah
Mareshah was an ancient fortified city of Judah, mentioned in the Hebrew Bible and located in the lowland region of southern Israel.
E1051606 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: Mareshah | Statement: [Shephelah, containsSite, Mareshah]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mareshah
Context triple: [Shephelah, containsSite, Mareshah]
  • A. Zahleh
    Zahleh is a major city in Lebanon’s Beqaa Valley, known for its predominantly Christian population, wineries, and role as a regional cultural and economic center.
  • B. Kafr Saqr
    Kafr Saqr is a city in northeastern Egypt known as one of the main urban centers of the Sharqia Governorate.
  • C. Ain El Mreisseh
    Ain El Mreisseh is a coastal neighborhood in Beirut, Lebanon, known for its seaside promenade, hotels, and proximity to the city’s central districts.
  • D. Tell al-Lahm
    Tell al-Lahm is an ancient archaeological mound in southern Iraq, believed to be the remains of a significant Mesopotamian settlement.
  • E. Shefa-'Amr
    Shefa-'Amr is a predominantly Arab city in northern Israel, known for its mixed Muslim, Christian, and Druze population and its location near Haifa in the Galilee region.
  • 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: Mareshah
Triple: [Shephelah, containsSite, Mareshah]
Generated description
Mareshah was an ancient fortified city of Judah, mentioned in the Hebrew Bible and located in the lowland region of southern Israel.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mareshah
Target entity description: Mareshah was an ancient fortified city of Judah, mentioned in the Hebrew Bible and located in the lowland region of southern Israel.
  • A. Zahleh
    Zahleh is a major city in Lebanon’s Beqaa Valley, known for its predominantly Christian population, wineries, and role as a regional cultural and economic center.
  • B. Kafr Saqr
    Kafr Saqr is a city in northeastern Egypt known as one of the main urban centers of the Sharqia Governorate.
  • C. Ain El Mreisseh
    Ain El Mreisseh is a coastal neighborhood in Beirut, Lebanon, known for its seaside promenade, hotels, and proximity to the city’s central districts.
  • D. Tell al-Lahm
    Tell al-Lahm is an ancient archaeological mound in southern Iraq, believed to be the remains of a significant Mesopotamian settlement.
  • E. Shefa-'Amr
    Shefa-'Amr is a predominantly Arab city in northern Israel, known for its mixed Muslim, Christian, and Druze population and its location near Haifa in the Galilee region.
  • 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_69d8076aae28819092cf636190ee5529 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbbe9c72c88190be3d7a3f2e96afbc completed April 12, 2026, 3:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69f77fa6a46881909d381d76d391f5b7 completed May 3, 2026, 5:02 p.m.
NEDg Description generation batch_69f782c41634819096b0939c6c917259 completed May 3, 2026, 5:15 p.m.
NED2 Entity disambiguation (via description) batch_69f78366eca88190be313c3a1b1e23ff completed May 3, 2026, 5:18 p.m.
Created at: April 9, 2026, 9:51 p.m.