Triple
T22449249
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pigeon Post |
E554944
|
entity |
| Predicate | mainCharactersGroup |
P24067
|
FINISHED |
| Object | Swallows |
—
|
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: Swallows | Statement: [Pigeon Post, mainCharactersGroup, Swallows]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Swallows Context triple: [Pigeon Post, mainCharactersGroup, Swallows]
-
A.
Swallows
chosen
The Swallows are a group of adventurous children who sail and camp in Arthur Ransome’s classic “Swallows and Amazons” series.
-
B.
Swallows
Swallows is a football club commonly known by this short name, referring to Mbabane Swallows F.C., one of Eswatini’s most prominent soccer teams.
-
C.
Swifts
Swifts is a renowned Russian military aerobatic display team known for performing precision maneuvers in fighter jets at major air shows.
-
D.
Flying Swallow
Flying Swallow is a poetic Japanese given name often associated with grace, speed, and agility, evoking the image of a swift, elegant bird in flight.
-
E.
Swallow
Swallow is the Allied reporting name for the Japanese World War II fighter aircraft Kawasaki Ki-61, known for its inline engine and resemblance to contemporary European fighters.
- 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_69e11e5113208190ab58c6b595f9d1d0 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15b4a20f8819097f471084e97e099 |
completed | April 29, 2026, 1:13 a.m. |
Created at: April 16, 2026, 8:48 p.m.