Triple
T34609789
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Old Course 18th green |
E888692
|
entity |
| Predicate | hasParContext |
P200581
|
FINISHED |
| Object | par-4 finishing hole |
—
|
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: par-4 finishing hole | Statement: [Old Course 18th green, hasParContext, par-4 finishing hole]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasParContext Context triple: [Old Course 18th green, hasParContext, par-4 finishing hole]
-
A.
hasPar
Indicates a relationship where one entity has another entity as its parent.
-
B.
hasParType
Indicates that an entity has a specific parent type or category to which it belongs.
-
C.
hasLanguageContext
Indicates that an entity is associated with or interpreted within a specific language or linguistic context.
-
D.
hasRuleContext
Indicates that an entity is associated with, governed by, or interpreted within a specific rule or set of rules that define its contextual behavior or constraints.
-
E.
hasCharacterContext
Indicates that a character is associated with or participates in a particular contextual situation, setting, or state.
- F. None of above. chosen
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_69f349d489d48190ba30e7d97c6f5ef9 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69ff97637ad881908c24fe2cc6b036db |
completed | May 9, 2026, 8:21 p.m. |
| PD | Predicate disambiguation | batch_69ff96c43a808190942eeda1934602db |
completed | May 9, 2026, 8:19 p.m. |
| PDg | Predicate description generation | batch_69ff976281888190a2e872296fb4a661 |
completed | May 9, 2026, 8:21 p.m. |
Created at: May 1, 2026, 2:03 a.m.