Triple

T30980931
Position Surface form Disambiguated ID Type / Status
Subject Tiburon as a railroad terminus E789369 entity
Predicate connectedAcross P58112 FINISHED
Object San Francisco Bay NE NERFINISHED

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: San Francisco Bay | Statement: [Tiburon as a railroad terminus, connectedAcross, San Francisco Bay]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: connectedAcross
Context triple: [Tiburon as a railroad terminus, connectedAcross, San Francisco Bay]
  • A. connectedByStraitTo chosen
    Indicates that one entity is geographically linked to another by a narrow body of water known as a strait.
  • B. formerlyConnectedTo
    Indicates that two entities were once connected or associated in some way, but that connection no longer exists.
  • C. partlyConnectedBy
    Indicates that two entities are linked or joined by something in an incomplete, partial, or not fully continuous way.
  • D. linkedNetwork
    Indicates that two entities are connected through a shared or associated network relationship.
  • E. associatedThrough
    Indicates that two entities are connected or related to each other by means of a specified intermediary, context, or linkage.
  • F. None of above.

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_69f224c4831c8190be53924ec25a150a completed April 29, 2026, 3:33 p.m.
NER Named-entity recognition batch_69fe744faca881908e11e90e0a35653f completed May 8, 2026, 11:39 p.m.
PD Predicate disambiguation batch_69fe734cbf7081909a552c5cf3b5ea59 completed May 8, 2026, 11:35 p.m.
Created at: April 29, 2026, 8:55 p.m.