Triple
T19118932
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zapotecs |
E467984
|
entity |
| Predicate | majorUrbanCenter |
P9892
|
FINISHED |
| Object | Yagul |
—
|
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: Yagul | Statement: [Zapotecs, majorUrbanCenter, Yagul]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yagul Context triple: [Zapotecs, majorUrbanCenter, Yagul]
-
A.
Yagul
chosen
Yagul is an important pre-Columbian archaeological site in Oaxaca, Mexico, known for its well-preserved Zapotec ruins and hilltop fortress.
-
B.
Yagüe
Yagüe is a Spanish surname most notably associated with Juan Yagüe, a prominent general during the Spanish Civil War.
-
C.
Kuku Yalaja
Kuku Yalaja is an Aboriginal Australian language traditionally spoken by the Kuku Yalanji people of far north Queensland.
-
D.
Echigoya
Echigoya was a pioneering Edo-period dry-goods store in Japan that evolved into what is now the Mitsukoshi department store chain.
-
E.
Guelatao
Guelatao is a Mexico City Metro station on Line A serving the eastern part of the city in the Iztapalapa borough.
- 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_69d8dd06a26481908039e2a1bae8c597 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e3c756a88190942930e6ae7242a7 |
completed | April 20, 2026, 8:28 a.m. |
Created at: April 10, 2026, 12:05 p.m.