Triple

T3404340
Position Surface form Disambiguated ID Type / Status
Subject Angers E71733 entity
Predicate twinCity P1072 FINISHED
Object Harar E221406 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: Harar | Statement: [Angers, twinCity, Harar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harar
Context triple: [Angers, twinCity, Harar]
  • A. Harar chosen
    Harar is a historic fortified city in eastern Ethiopia renowned for its ancient Islamic heritage, distinctive city walls, and status as a UNESCO World Heritage Site.
  • B. Gash‑Barka
    Gash‑Barka is a largely agricultural region in southwestern Eritrea known for its fertile land and role as one of the country’s main food-producing areas.
  • C. Dakhla
    Dakhla is a coastal city in Western Sahara known for its strategic Atlantic location, fishing industry, and popularity as a wind- and kitesurfing destination.
  • D. Tarhuna
    Tarhuna is a town in northwestern Libya, southeast of Tripoli, known for its strategic role and tribal influence during the Libyan civil conflicts.
  • E. Gondar
    Gondar is a historic city in northern Ethiopia renowned for its well-preserved medieval castles and churches, often called the "Camelot of Africa."
  • 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_69ad85aac4808190a092c9cc8911f584 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb8e8ea848190b4ac167f1aba8ebd completed March 8, 2026, 5:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69b34bd69f388190981da6454dfd4fb1 completed March 12, 2026, 11:27 p.m.
Created at: March 8, 2026, 3:14 p.m.