Triple
T15698638
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kot Diji archaeological mound |
E380534
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Kot Diji |
E78478
|
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: Kot Diji | Statement: [Kot Diji archaeological mound, locatedIn, Kot Diji]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kot Diji Context triple: [Kot Diji archaeological mound, locatedIn, Kot Diji]
-
A.
Kot Diji
chosen
Kot Diji is an ancient archaeological and fort site in Sindh, Pakistan, known for its pre-Harappan settlement remains and well-preserved early 19th-century fort.
-
B.
Kot Addu
Kot Addu is a prominent city in Pakistan known for its strategic location in southern Punjab and its role as a regional commercial and agricultural hub.
-
C.
Koṭa
Koṭa is a Dravidian language spoken by the indigenous Kota people in the Nilgiri Hills of southern India.
-
D.
Kutha
Kutha was an ancient Mesopotamian city best known as the principal cult center of the underworld god Nergal.
-
E.
Kahuta
Kahuta is a town in Pakistan’s Punjab province known for hosting the country’s primary nuclear research and enrichment facilities.
- 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_69d86d99e860819094b6957cde470f2c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04f6c3328819081325b702ca92862 |
completed | April 16, 2026, 2:54 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff7571f1888190b83af75ec9c7432b |
completed | May 9, 2026, 5:57 p.m. |
Created at: April 10, 2026, 4:44 a.m.