Triple
T21042892
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wajo |
E518372
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Tempe |
—
|
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: Tempe | Statement: [Wajo, capital, Tempe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tempe Context triple: [Wajo, capital, Tempe]
-
A.
Tempe
Tempe is a city in the Phoenix metropolitan area of Arizona, known for being home to Arizona State University and its vibrant college-town atmosphere.
-
B.
Tempe
chosen
Tempe is a town in South Sulawesi, Indonesia, serving as the administrative center of Wajo Regency.
-
C.
Tempe
Tempe is a locality within Saint George Parish on the Caribbean island nation of Grenada.
-
D.
Tucson
Tucson is a major city in southern Arizona known for its desert landscape, rich Native American and Mexican cultural influences, and the University of Arizona.
-
E.
Tempe Valley
Tempe Valley is a narrow, scenic gorge in the region of Thessaly in central Greece, historically renowned for its natural beauty and mythological associations.
- 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_69e0b50438e08190917e2538bb8bc034 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fcf1950081908ff9fe8719e1e81b |
completed | April 21, 2026, 4:28 a.m. |
Created at: April 16, 2026, 2:17 p.m.