Triple

T8990358
Position Surface form Disambiguated ID Type / Status
Subject EGIS E214772 entity
Predicate shortName P43 FINISHED
Object EGIS E214772 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: EGIS | Statement: [EGIS, shortName, EGIS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: EGIS
Context triple: [EGIS, shortName, EGIS]
  • A. EGIS chosen
    EGIS is the principal intelligence agency of Egypt, responsible for national security, foreign intelligence, and counterintelligence operations.
  • B. IGIS
    IGIS is the acronym for Australia’s Inspector-General of Intelligence and Security, an independent oversight body that monitors the legality and propriety of the country’s intelligence agencies.
  • C. EGS
    EGS is a NASA program responsible for developing and operating the ground infrastructure and launch processing systems that support the agency’s deep space exploration missions, including Artemis.
  • D. ESGP
    ESGP is the ICAO airport code for Gothenburg City Airport, a regional airport serving the Gothenburg area in Sweden.
  • E. GEOVIA
    GEOVIA is a Dassault Systèmes software brand focused on modeling and simulating the earth’s resources for mining, geology, and urban planning.
  • 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_69ca839f76bc8190a4b7123cdd682199 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc68733548819096a5ba0ff41e43da completed April 1, 2026, 12:36 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfd0c9659c8190ae7ff5df8e016d17 completed April 3, 2026, 2:38 p.m.
Created at: March 30, 2026, 7:04 p.m.