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.