Triple
T6561741
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tektitek |
E153798
|
entity |
| Predicate | closelyRelatedTo |
P37
|
FINISHED |
| Object | Mam |
E86612
|
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: Mam | Statement: [Tektitek, closelyRelatedTo, Mam]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mam Context triple: [Tektitek, closelyRelatedTo, Mam]
-
A.
Mam
chosen
Mam is a Mayan language spoken primarily by the Mam people in the western highlands of Guatemala and parts of southern Mexico.
-
B.
MAM
MAM is a prominent modern art museum in Mexico City known for its extensive collection of 20th- and 21st-century Mexican and international artworks.
-
C.
Mamu
Mamu is a notable Odia novel by Fakir Mohan Senapati that satirically portrays social and political life in colonial Odisha.
-
D.
MAMAC
MAMAC is a modern and contemporary art museum in Nice, France, known for its collections of postwar European and American art.
-
E.
Mamayi
Mamayi was a powerful 14th-century military and political leader of the Golden Horde who played a central role in its internal power struggles and conflicts with emerging Russian principalities.
- 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_69c6880cb35881909b763eb0125236b9 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6ae38e94081908f964d130f9147d8 |
completed | March 27, 2026, 4:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c6d55fa1bc81908f2929e835051532 |
completed | March 27, 2026, 7:07 p.m. |
Created at: March 27, 2026, 1:52 p.m.