Triple

T22449871
Position Surface form Disambiguated ID Type / Status
Subject Sagamore Spirit E554961 entity
Predicate hasTiesTo P7843 FINISHED
Object horse farm Sagamore Farm LITERAL 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: horse farm Sagamore Farm | Statement: [Sagamore Spirit, hasTiesTo, horse farm Sagamore Farm]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasTiesTo
Context triple: [Sagamore Spirit, hasTiesTo, horse farm Sagamore Farm]
  • A. hasTiePossibility
    Indicates that a situation, event, or interaction has the potential to end in a tie or draw rather than producing a single winner.
  • B. hasHistoricalTieTo chosen
    Indicates a relationship where one entity is historically connected or linked to another through past events, associations, or influences.
  • C. hasStrongTiesTo
    Indicates a close, influential, and enduring relationship or connection exists between the referenced entities.
  • D. maintainsTieWith
    Indicates that one entity keeps an ongoing connection or relationship with another entity over time.
  • E. hasTieDowns
    Indicates that an object, structure, or vehicle is equipped with tie-down points or devices for securing loads or attachments.
  • 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_69e11e5113208190ab58c6b595f9d1d0 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15b4ae8a08190ba6027f036ce62af completed April 29, 2026, 1:13 a.m.
PD Predicate disambiguation batch_69e898ad961c819098fd1e46129bddcc completed April 22, 2026, 9:45 a.m.
Created at: April 16, 2026, 8:48 p.m.