Triple
T21109171
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gulzar |
E520129
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Maachis |
—
|
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: Maachis | Statement: [Gulzar, notableWork, Maachis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Maachis Context triple: [Gulzar, notableWork, Maachis]
-
A.
Maachis
chosen
Maachis is a 1996 Indian political thriller film directed by Gulzar that explores youth radicalization and insurgency in the aftermath of the 1984 anti-Sikh riots.
-
B.
Alara of Nubia
Alara of Nubia was an early Kushite king credited with founding the Napatan dynasty and laying the foundations for the later Nubian control of Egypt’s 25th Dynasty.
-
C.
Taharka
Taharka was a pharaoh of Egypt’s 25th (Kushite) Dynasty, known for his extensive building projects and for resisting Assyrian expansion in the 7th century BCE.
-
D.
Puabi
Puabi was a prominent Sumerian queen or high priestess from the Early Dynastic period, best known for her richly furnished tomb discovered at the ancient city of Ur.
-
E.
Makeda
"Makeda" is a popular neo-soul/R&B song by the French duo Les Nubians, known for its smooth harmonies and Afrocentric themes.
- 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_69e0b509a318819092fbbcb21d1fe603 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7210110a48190a6359b6732f6293d |
completed | April 21, 2026, 7:02 a.m. |
Created at: April 16, 2026, 2:54 p.m.