Triple
T20941497
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TAN public transport network |
E515732
|
entity |
| Predicate | hasOperator |
P179
|
FINISHED |
| Object | SEMITAN |
—
|
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: SEMITAN | Statement: [TAN public transport network, hasOperator, SEMITAN]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SEMITAN Context triple: [TAN public transport network, hasOperator, SEMITAN]
-
A.
SEMITAN
chosen
SEMITAN is the public transport authority and operating company responsible for managing buses, trams, and related services in the Nantes metropolitan area of France.
-
B.
יהודה
יהודה הוא אחד מבני יעקב, שממנו יצאה שבט יהודה המרכזי בעם ישראל והמסורת מייחסת לו תפקיד חשוב בהתפתחות ההנהגה והמלכות בישראל.
-
C.
Jood
Jood is a dam associated with the Fantastic Light lineage, likely serving as a key broodmare or progenitor in Thoroughbred horse breeding.
-
D.
Shemia
Shemia is an American politician and attorney best known for serving as Oregon’s Secretary of State.
-
E.
Donmeh
The Donmeh were a secretive group of crypto-Jews in the Ottoman Empire who outwardly converted to Islam while secretly following the messianic teachings of Shabbetai Tzvi.
- 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_69e0b4fc13408190b06868df03c5c29b |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6f955f0148190ae42278ad5c0f363 |
completed | April 21, 2026, 4:13 a.m. |
Created at: April 16, 2026, 12:50 p.m.