Triple
T3448930
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New York City Marathon |
E72744
|
entity |
| Predicate | hasExpo |
P48875
|
FINISHED |
| Object | pre-race marathon expo for bib pickup |
—
|
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: pre-race marathon expo for bib pickup | Statement: [New York City Marathon, hasExpo, pre-race marathon expo for bib pickup]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasExpo Context triple: [New York City Marathon, hasExpo, pre-race marathon expo for bib pickup]
-
A.
hasEP
Indicates that an entity possesses, is associated with, or is characterized by a specific EP (e.g., an endpoint, event point, or designated EP resource) in the given context.
-
B.
hasMP
Indicates that an entity is represented by, or associated with, a specific Member of Parliament (MP).
-
C.
hasExpansion
Indicates that one entity serves as a larger, extended, or elaborated form of another entity.
-
D.
hasAperture
Indicates that one entity possesses or is characterized by a specific opening, gap, or aperture.
-
E.
exposes
Indicates making something visible, known, or vulnerable by removing cover, concealment, or protection.
- 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_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. |
| PDg | Predicate description generation | batch_69adb1ecb02881908394f197e31431b4 |
completed | March 8, 2026, 5:29 p.m. |
Created at: March 8, 2026, 3:16 p.m.