Triple
T17952719
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shani |
E448870
|
entity |
| Predicate | consort |
P13
|
FINISHED |
| Object | Manda |
—
|
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: Manda | Statement: [Shani, consort, Manda]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Manda Context triple: [Shani, consort, Manda]
-
A.
Manda
Manda is a lesser-known Dravidian language spoken by tribal communities in parts of eastern India, particularly in Odisha.
-
B.
Manda
chosen
Manda is a serpentine kaiju from the Godzilla franchise, known as an ancient sea dragon that appears in several Toho monster films.
-
C.
Mandas
Mandas is a small historic town and comune in the Province of South Sardinia, Italy, known for its traditional Sardinian culture and rural landscape.
-
D.
Mandarmani
Mandarmani is a seaside resort village in West Bengal, India, known for its long, drivable beach and growing popularity as a quieter alternative to busier coastal destinations.
-
E.
Mandabi
Mandabi is a 1968 Senegalese film by Ousmane Sembène that satirically portrays postcolonial bureaucracy and social inequality through the story of a man trying to cash a money order.
- 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_69d8b9f8cca8819099836916c56b7c95 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4afad61f481908b34cd24de88983c |
completed | April 19, 2026, 10:34 a.m. |
Created at: April 10, 2026, 10:21 a.m.