Triple
T3448918
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New York City Marathon |
E72744
|
entity |
| Predicate | hasCharityProgram |
P8514
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [New York City Marathon, hasCharityProgram, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCharityProgram Context triple: [New York City Marathon, hasCharityProgram, true]
-
A.
hasCharitySingle
Indicates that an entity is associated with exactly one specific charitable organization or charitable initiative.
-
B.
hasVolunteerProgram
Indicates that an organization or entity offers an organized program through which individuals can volunteer their time or services.
-
C.
hasCharitableFoundation
Indicates that an entity maintains or is associated with a charitable foundation, typically for philanthropic or nonprofit activities.
-
D.
associatedCharity
chosen
Indicates that one entity has a formal or recognized charitable affiliation or partnership with another entity.
-
E.
philanthropicInitiative
Indicates an action or relationship where an entity undertakes or supports activities intended to promote the welfare of others, typically through charitable or socially beneficial efforts.
- 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_69ad85b05c848190b7a28ceec2bd7b74 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adba71f4a4819089d08b871cc9b16f |
completed | March 8, 2026, 6:05 p.m. |
| PD | Predicate disambiguation | batch_69adae0255b48190a9069f7871c7a012 |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:16 p.m.