Triple
T23084078
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harlem Air Shaft |
E575556
|
entity |
| Predicate | hasTitleWord |
P3254
|
FINISHED |
| Object | Air |
—
|
NE NERFINISHED |
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: Air | Statement: [Harlem Air Shaft, hasTitleWord, Air]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Air Context triple: [Harlem Air Shaft, hasTitleWord, Air]
-
A.
Air
"Air" is a 2023 biographical sports drama film directed by Ben Affleck that chronicles Nike's pursuit of a young Michael Jordan, in which Matt Damon stars as talent scout Sonny Vaccaro.
-
B.
Air
chosen
Air is a French electronic music duo known for their atmospheric, downtempo sound and influential albums like "Moon Safari."
-
C.
Air Apparent
Air Apparent is a fantasy novel in Piers Anthony’s long-running Xanth series, known for its pun-filled world and humorous magical adventures.
-
D.
Airflow
Airflow is an open-source platform for authoring, scheduling, and monitoring complex data workflows as directed acyclic graphs.
-
E.
Airai
Airai is a state in the Republic of Palau known for hosting the country’s main international airport and serving as a key gateway to the islands.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245bf3e3c819086d3448720efc01b |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18da3d4208190b7bfd1026e773dbf |
completed | April 29, 2026, 4:48 a.m. |
Created at: April 17, 2026, 3:57 p.m.