Triple
T20299662
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Manu National Park |
E505444
|
entity |
| Predicate | governingBody |
P46
|
FINISHED |
| Object | SERNANP |
—
|
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: SERNANP | Statement: [Manu National Park, governingBody, SERNANP]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SERNANP Context triple: [Manu National Park, governingBody, SERNANP]
-
A.
SERNANP
chosen
SERNANP is Peru’s national authority responsible for managing and conserving the country’s system of protected natural areas.
-
B.
Sert
Sert is the surname of Josep Lluís Sert, a prominent 20th-century Spanish architect known for his modernist designs and leadership at Harvard’s Graduate School of Design.
-
C.
SARON
SARON is a Swiss franc overnight reference interest rate used as a robust alternative to LIBOR in financial markets.
-
D.
Seryl
Seryl is a feminine given name most notably borne by Seryl Kushner, a New York real estate figure and mother of businessman Charles Kushner.
-
E.
SERI
SERI is Switzerland’s federal authority responsible for national policies and coordination in education, research, and innovation.
- 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_69e0b4b8ab648190906e18538c250148 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6770b9484819090ffcb339f2a435a |
completed | April 20, 2026, 6:57 p.m. |
Created at: April 16, 2026, 11:16 a.m.