Triple
T7258382
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oraibi |
E159580
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Bacavi |
E166975
|
NE FINISHED |
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: Bacavi | Statement: [Oraibi, near, Bacavi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bacavi Context triple: [Oraibi, near, Bacavi]
-
A.
Bacavi
chosen
Bacavi is a traditional Hopi village located on the Hopi Reservation in northeastern Arizona.
-
B.
Bhaca
Bhaca are a Xhosa-related ethnic group of South Africa known for their distinct language variety, cultural traditions, and historical chiefdoms in the Eastern Cape region.
-
C.
Barshaini
Barshaini is a small Himalayan village in Himachal Pradesh, India, that serves as a popular base and trailhead for treks into the Parvati Valley and surrounding high-altitude landscapes.
-
D.
Vabis
Vabis was a Swedish automotive and engineering company that later merged to form Scania-Vabis, a predecessor of the modern Scania AB.
-
E.
Batha
Batha is a central region of Chad known for its semi-arid Sahelian landscape and traditional pastoralist communities.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69c68838f9948190875fd60b2351230c |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6eac340a0819084015a5fbf7a5539 |
completed | March 27, 2026, 8:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7d3b99af08190a28d77e7363edf45 |
completed | March 28, 2026, 1:12 p.m. |
Created at: March 27, 2026, 2:57 p.m.