Triple
T22999095
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Altair |
E572585
|
entity |
| Predicate | hasProperName |
P27536
|
FINISHED |
| Object | Altair |
—
|
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: Altair | Statement: [Altair, hasProperName, Altair]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Altair Context triple: [Altair, hasProperName, Altair]
-
A.
Altair
chosen
Altair is a bright, nearby A-type main-sequence star in the constellation Aquila and one of the three stars forming the prominent Summer Triangle asterism.
-
B.
Alioth
Alioth is a prominent white star in the constellation Ursa Major and one of the main stars forming the Big Dipper asterism.
-
C.
Axius
Axius is the ancient name of the Orontes River, a historically significant waterway in the Near East that flows through modern-day Lebanon, Syria, and Turkey.
-
D.
Solari
Solari is an Italian surname associated with several notable figures, including architects, artists, and athletes.
-
E.
Solara
Solara is a young woman in the post-apocalyptic film "The Book of Eli" who becomes Eli’s companion and protégé on his journey to protect a sacred book.
- 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_69e245b6a3ac81908087599eefe3e365 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f182f54ce88190930530958e2a1830 |
completed | April 29, 2026, 4:03 a.m. |
Created at: April 17, 2026, 3:50 p.m.