Triple

T4190167
Position Surface form Disambiguated ID Type / Status
Subject SXSW E89014 entity
Predicate hasComponent P35 FINISHED
Object SXSW Interactive E89014 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: SXSW Interactive | Statement: [SXSW, hasComponent, SXSW Interactive]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SXSW Interactive
Context triple: [SXSW, hasComponent, SXSW Interactive]
  • A. SXSW festival chosen
    The SXSW festival is a major annual event in Austin, Texas that showcases music, film, and interactive media, drawing artists, innovators, and audiences from around the world.
  • B. CES
    CES is a high-resolution astronomical spectrograph used on the ESO 3.6-metre telescope for detailed spectroscopic studies of celestial objects.
  • C. CES
    CES is the station code used to identify Cessnock subway station on the Glasgow Subway network.
  • D. CES
    CES is the ICAO airline designator used to identify China Eastern Airlines in international aviation operations.
  • E. CES
    CES is the commonly used abbreviation for the U.S. Committee on Economic Security, the New Deal–era body that helped design foundational social welfare programs like Social Security.
  • 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_69aed9569a4481908b6c1fcec2a11e21 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af033ef6648190adde17f943d89c78 completed March 9, 2026, 5:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69b58a05e634819094bbe145f86d8786 completed March 14, 2026, 4:17 p.m.
Created at: March 9, 2026, 3:46 p.m.