Triple
T22315203
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ngo dynasty |
E551622
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Co Loa |
—
|
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: Co Loa | Statement: [Ngo dynasty, capital, Co Loa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Co Loa Context triple: [Ngo dynasty, capital, Co Loa]
-
A.
Co Loa
chosen
Co Loa is an ancient fortified city and archaeological site that served as the capital of the early Vietnamese Âu Lạc kingdom.
-
B.
Supai
Supai is a small, remote village within the Havasupai Indian Reservation in the Grand Canyon, Arizona, known for its stunning turquoise waterfalls and being one of the most isolated communities in the United States.
-
C.
Sinkyone
Sinkyone is an extinct Athabaskan language once spoken by the Sinkyone people of northern California’s Pacific coast.
-
D.
Black Kaweah
Black Kaweah is a prominent, rugged peak in California’s Sierra Nevada, known for its dark rock and challenging climbing routes.
-
E.
Lo’ak
Lo’ak is a central Na’vi character in James Cameron’s Avatar film series, known as the rebellious and empathetic son of Jake Sully and Neytiri.
- 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_69e11e4776588190abb21e5cea79973f |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1575287688190aa642bb49b24f5a1 |
completed | April 29, 2026, 12:56 a.m. |
Created at: April 16, 2026, 8:42 p.m.