Triple

T28712322
Position Surface form Disambiguated ID Type / Status
Subject Ebla E729861 entity
Predicate languageOfTablets P142268 FINISHED
Object Eblaite
Eblaite is an extinct Semitic language once spoken in the ancient city of Ebla in modern-day Syria, known primarily from thousands of cuneiform tablets dating to the third millennium BCE.
 E1829845 NE FINISHED

How this triple was built (3 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: Eblaite | Statement: [Ebla, languageOfTablets, Eblaite]
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: Eblaite
Triple: [Ebla, languageOfTablets, Eblaite]
Generated description
Eblaite is an extinct Semitic language once spoken in the ancient city of Ebla in modern-day Syria, known primarily from thousands of cuneiform tablets dating to the third millennium BCE.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: languageOfTablets
Context triple: [Ebla, languageOfTablets, Eblaite]
  • A. tabletsLanguage chosen
    Indicates that the language used on or in the tablets is a particular specified language.
  • B. tabletForm
    Indicates that something exists or is provided in tablet dosage form.
  • C. writingTabletsContent
    Indicates that one or more writing tablets contain or bear a particular written content.
  • D. languageOfProduct
    Indicates the language in which a product is written, labeled, presented, or otherwise made available.
  • E. occursInTablet
    Indicates that an event, statement, or item is recorded or found within a specific tablet.
  • F. None of above.

Provenance (6 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_69f043e7d5a4819094b18aca10b1e024 completed April 28, 2026, 5:21 a.m.
NER Named-entity recognition batch_69fe163a41a0819098403b470e327d29 completed May 8, 2026, 4:58 p.m.
NED1 Entity disambiguation (via context triple) batch_6a1ccf5666d48190a5a54288bdbea1d2 completed June 1, 2026, 12:16 a.m.
NEDg Description generation batch_6a1cd021944881908cae19ba344f1184 completed June 1, 2026, 12:19 a.m.
NED2 Entity disambiguation (via description) batch_6a24945efab88190a4ccb8a92331e469 completed June 6, 2026, 9:42 p.m.
PD Predicate disambiguation batch_69fe1358db5c819092570814a37ef5bd completed May 8, 2026, 4:46 p.m.
Created at: April 28, 2026, 5:48 a.m.