Triple
T19782543
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Manu Temple |
E475173
|
entity |
| Predicate | dedicatedTo |
P500
|
FINISHED |
| Object | sage Manu |
—
|
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: sage Manu | Statement: [Manu Temple, dedicatedTo, sage Manu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: sage Manu Context triple: [Manu Temple, dedicatedTo, sage Manu]
-
A.
Sage Manu
chosen
Sage Manu is the legendary Hindu lawgiver and progenitor of mankind, traditionally regarded as the author of the ancient legal and ethical text Manusmriti.
-
B.
Sage
Sage is a translucent, greenish color variant used on certain models of Apple's iMac G3 computers.
-
C.
Sage
Sage is a surname most notably associated with American actress Halston Sage, known for her roles in film and television.
-
D.
MANU
MANU is the acronym for the Macedonian Academy of Sciences and Arts, the leading national institution for scientific and artistic research in North Macedonia.
-
E.
Simanu
Simanu is a month in the ancient Babylonian calendar, corresponding roughly to late spring or early summer in the modern Gregorian calendar.
- 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_69d8e51b014081908b263e167370529a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e653852e848190b8971981a164e8f9 |
completed | April 20, 2026, 4:25 p.m. |
Created at: April 10, 2026, 1:49 p.m.