Triple
T7309177
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harappa |
E168047
|
entity |
| Predicate | hasWritingSystem |
P454
|
FINISHED |
| Object | Indus script |
E169855
|
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: Indus script | Statement: [Harappa, hasWritingSystem, Indus script]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Indus script Context triple: [Harappa, hasWritingSystem, Indus script]
-
A.
Indus script
chosen
The Indus script is an undeciphered system of symbols used by the ancient Indus Valley Civilization, known from short inscriptions on seals, tablets, and pottery dating to around 2600–1900 BCE.
-
B.
Prachalit script
Prachalit script is a historical Brahmic writing system used primarily for the Nepal Bhasa (Newar) language of the Kathmandu Valley.
-
C.
Brahmi script
The Brahmi script is one of the oldest writing systems of the Indian subcontinent, serving as the ancestor of most modern South and Southeast Asian scripts.
-
D.
Kharoṣṭhī script
The Kharoṣṭhī script is an ancient right-to-left writing system used in northwestern South Asia, especially in the Gandhāra region, primarily for early Buddhist and administrative texts.
-
E.
Tirhuta script
Tirhuta script is a traditional Brahmic writing system historically used for the Maithili language of the Mithila region in India and Nepal.
- 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_69c6888d8e3c81909db79714903baf31 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6ebda7b748190a230a22ecea79342 |
completed | March 27, 2026, 8:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7e567df3c8190a1baaa7ef9c99d87 |
completed | March 28, 2026, 2:27 p.m. |
Created at: March 27, 2026, 3:01 p.m.