Triple

T14326933
Position Surface form Disambiguated ID Type / Status
Subject Epiphania E355238 entity
Predicate hasArchaeologicalSite P1098 FINISHED
Object Hama tell E71751 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: Hama tell | Statement: [Epiphania, hasArchaeologicalSite, Hama tell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hama tell
Context triple: [Epiphania, hasArchaeologicalSite, Hama tell]
  • A. Hama Tuma
    Hama Tuma is an Ethiopian writer and political satirist known for his sharp, critical short stories and essays that challenge authoritarianism and social injustice.
  • B. Hama chosen
    Hama is a major city in west-central Syria, historically known for its ancient waterwheels (norias) on the Orontes River and its role as an important agricultural and industrial center.
  • C. H•A•M
    H•A•M is a hard-hitting, Lex Luger–produced hip-hop track by Jay-Z and Kanye West that showcases their aggressive, boastful lyricism and opulent Watch the Throne-era sound.
  • D. HMA
    HMA is a European network of national medicines regulatory authorities that collaborates to ensure the quality, safety, and efficacy of medicinal products across member states.
  • E. Hamap
    Hamap is a Papuan language spoken on the Alor–Pantar archipelago in eastern Indonesia.
  • 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_69d8278fa2108190bc0d0e7939c1eb03 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de8c1c3e70819084b6728ac5c18561 completed April 14, 2026, 6:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd4690a79c819099cc4ae9a10ba0db completed May 8, 2026, 2:12 a.m.
Created at: April 10, 2026, 1:13 a.m.