Triple
T4738487
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brahmana |
E105181
|
entity |
| Predicate | follows |
P134
|
FINISHED |
| Object | Samhitas |
E110820
|
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: Samhitas | Statement: [Brahmana, follows, Samhitas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Samhitas Context triple: [Brahmana, follows, Samhitas]
-
A.
Brahmanas
The Brahmanas are a collection of ancient Indian prose texts that explain the rituals, ceremonies, and symbolic meanings of the Vedic hymns.
-
B.
Āraṇyaka
Āraṇyakas are a class of ancient Hindu sacred texts that serve as a bridge between the ritual-focused Brāhmaṇas and the philosophical Upaniṣads, exploring the deeper, often symbolic meaning of Vedic rituals.
-
C.
Vedas
The Vedas are a collection of ancient sacred texts composed in Sanskrit that form the foundational spiritual and philosophical scriptures of Hinduism.
-
D.
Samhita
chosen
Samhita is the mantra-collection portion of the Yajurveda, comprising its core liturgical hymns and formulas used in Vedic rituals.
-
E.
Jatavedas
Jatavedas is a prominent Vedic epithet of the fire god Agni, highlighting his all-knowing, all-consuming nature as the divine flame that permeates and witnesses all.
- 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_69bd43ef87a48190a5bc3600711aa032 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6485d690819098dc4a974516da6b |
completed | March 20, 2026, 3:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be10b8e7ec81908cc1ec9b94a6bee4 |
completed | March 21, 2026, 3:30 a.m. |
Created at: March 20, 2026, 1:19 p.m.