Triple

T17194663
Position Surface form Disambiguated ID Type / Status
Subject Scythian religion E417316 entity
Predicate hasDeity P5606 FINISHED
Object Tabiti
Tabiti is the Scythian goddess of the hearth and fire, revered as a central protective and domestic deity in their pantheon.
 E1255169 NE FINISHED

How this triple was built (4 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: Tabiti | Statement: [Scythian religion, hasDeity, Tabiti]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tabiti
Context triple: [Scythian religion, hasDeity, Tabiti]
  • A. Tabiriyya
    Tabiriyya is a sub-school within the Zaydi branch of Shia Islam, representing a distinct theological and legal tradition in that sect.
  • B. El Tebbin
    El Tebbin is an industrial district in southern Cairo, Egypt, known for its steel and heavy manufacturing facilities.
  • C. Kabiyesi
    Kabiyesi is a Yoruba honorific style of address reserved for paramount traditional rulers, signifying their supreme and unquestionable authority.
  • D. Tübatulabal
    Tübatulabal is a Native American people and their Uto-Aztecan language traditionally associated with the Kern River region of California.
  • E. Taloot
    Taloot is a coastal barangay of the municipality of Argao in Cebu, Philippines.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Tabiti
Triple: [Scythian religion, hasDeity, Tabiti]
Generated description
Tabiti is the Scythian goddess of the hearth and fire, revered as a central protective and domestic deity in their pantheon.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tabiti
Target entity description: Tabiti is the Scythian goddess of the hearth and fire, revered as a central protective and domestic deity in their pantheon.
  • A. Tabiriyya
    Tabiriyya is a sub-school within the Zaydi branch of Shia Islam, representing a distinct theological and legal tradition in that sect.
  • B. El Tebbin
    El Tebbin is an industrial district in southern Cairo, Egypt, known for its steel and heavy manufacturing facilities.
  • C. Kabiyesi
    Kabiyesi is a Yoruba honorific style of address reserved for paramount traditional rulers, signifying their supreme and unquestionable authority.
  • D. Tübatulabal
    Tübatulabal is a Native American people and their Uto-Aztecan language traditionally associated with the Kern River region of California.
  • E. Taloot
    Taloot is a coastal barangay of the municipality of Argao in Cebu, Philippines.
  • F. None of above. chosen

Provenance (5 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_69d886d6ba8c819093215917b3d01689 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42da9e6208190b5c4e5925e840217 completed April 19, 2026, 1:19 a.m.
NED1 Entity disambiguation (via context triple) batch_6a015fd5f834819080ad2a2ffdc017b6 completed May 11, 2026, 4:49 a.m.
NEDg Description generation batch_6a0160ce18e88190af8e3a7dfc17536a completed May 11, 2026, 4:53 a.m.
NED2 Entity disambiguation (via description) batch_6a016146ce14819091e3459d25ca19aa completed May 11, 2026, 4:55 a.m.
Created at: April 10, 2026, 5:38 a.m.