Triple

T8955763
Position Surface form Disambiguated ID Type / Status
Subject Conference of Parties to the 2005 Convention E213467 entity
Predicate firstSessionHeldAt P28016 FINISHED
Object Paris E568 NE FINISHED

How this triple was built (3 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: Paris | Statement: [Conference of Parties to the 2005 Convention, firstSessionHeldAt, Paris]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paris
Context triple: [Conference of Parties to the 2005 Convention, firstSessionHeldAt, Paris]
  • A. Paris
    Paris is a prince of Troy in Greek mythology, best known for judging the beauty contest of the goddesses and for abducting Helen, which sparked the Trojan War.
  • B. Paris chosen
    Paris is the capital and largest city of France, renowned for its historic architecture, art, fashion, and cultural influence worldwide.
  • C. Paris
    Paris is a major Chilean department store and retail chain offering a wide range of apparel, home goods, and consumer products.
  • D. Paris
    Paris is a budget-oriented AMD Sempron processor core designed for entry-level desktop computing.
  • E. Parigi
    Parigi is a coastal town that serves as the administrative center of Parigi Moutong Regency in Central Sulawesi, Indonesia.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: firstSessionHeldAt
Context triple: [Conference of Parties to the 2005 Convention, firstSessionHeldAt, Paris]
  • A. firstSessionHeldIn chosen
    Indicates that the initial or inaugural session of an event, activity, or process took place in a specified location or context.
  • B. firstSessionStart
    Indicates the point in time when an entity’s very first session or interaction begins.
  • C. firstHeldAt
    Indicates the initial time or event at which an entity was first held, possessed, or hosted.
  • D. dateOfFirstMeeting
    Indicates the specific date on which two or more entities first met or came together.
  • E. firstIntroductionDate
    Indicates the date on which an entity was first introduced or presented for the first time.
  • F. None of above.

Provenance (4 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_69ca8399ad2081909f8fa41d4314c215 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc6726cec48190a900ae52b1522adb completed April 1, 2026, 12:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfc923ee708190a669749ad0752204 completed April 3, 2026, 2:05 p.m.
PD Predicate disambiguation batch_69cc5ed74d288190b712d739805579dc completed March 31, 2026, 11:55 p.m.
Created at: March 30, 2026, 7 p.m.