Triple

T16865571
Position Surface form Disambiguated ID Type / Status
Subject Eden E410026 entity
Predicate mentionedWith P63729 FINISHED
Object Gihon E464108 NE FINISHED

How this triple was built (2 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: Gihon | Statement: [Eden, mentionedWith, Gihon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gihon
Context triple: [Eden, mentionedWith, Gihon]
  • A. Gihon Spring chosen
    Gihon Spring is an ancient freshwater source in Jerusalem, historically vital as the city’s main water supply and central to its early settlement and defenses.
  • B. Ayalon River
    The Ayalon River is a short, largely channelized river in central Israel that runs through the Tel Aviv metropolitan area and plays a key role in its drainage and transportation corridor.
  • C. Yarkon River
    The Yarkon River is a major coastal river in central Israel that flows through the Tel Aviv metropolitan area into the Mediterranean Sea.
  • D. Kishon River
    The Kishon River is a major watercourse in northern Israel that flows from the Jezreel Valley to the Mediterranean Sea near Haifa.
  • E. Gilo River
    The Gilo River is a significant river in western Ethiopia and South Sudan, known as a tributary of the Sobat River within the Nile Basin.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d88395e6c88190b22730f335107c14 completed April 10, 2026, 4:59 a.m.
NER Named-entity recognition batch_69e3b506dd1c81909ab8006b6a1e2b7a completed April 18, 2026, 4:44 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00c2a929b081909d3a5a680ae93a78 completed May 10, 2026, 5:38 p.m.
Created at: April 10, 2026, 5:24 a.m.