Triple

T4944159
Position Surface form Disambiguated ID Type / Status
Subject Theatre of Dionysus E111005 entity
Predicate hasPart P35 FINISHED
Object skene
The skene was a structure at the back of the ancient Greek theater stage that served as both a backdrop for performances and a space for actors to change costumes and enter the scene.
 E481176 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: skene | Statement: [Theatre of Dionysus, hasPart, skene]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: skene
Context triple: [Theatre of Dionysus, hasPart, skene]
  • A. Scaniarinken
    Scaniarinken is a multi-purpose indoor arena in Södertälje, Sweden, best known as the home venue for the ice hockey club Södertälje SK.
  • B. SKN
    SKN is the station code for South Kensington tube station, a major London Underground interchange serving the South Kensington area.
  • C. Skamneli
    Skamneli is a traditional mountain village in the Zagori region of Epirus, northwestern Greece, known for its stone-built architecture and scenic natural surroundings.
  • D. Schney
    Schney is a district or locality within the town of Lichtenfels in the Upper Franconia region of Bavaria, Germany.
  • E. Skjåk
    Skjåk is a rural municipality in Innlandet county, Norway, known for its mountainous landscapes, national parks, and dry inland climate.
  • 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: skene
Triple: [Theatre of Dionysus, hasPart, skene]
Generated description
The skene was a structure at the back of the ancient Greek theater stage that served as both a backdrop for performances and a space for actors to change costumes and enter the scene.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: skene
Target entity description: The skene was a structure at the back of the ancient Greek theater stage that served as both a backdrop for performances and a space for actors to change costumes and enter the scene.
  • A. Scaniarinken
    Scaniarinken is a multi-purpose indoor arena in Södertälje, Sweden, best known as the home venue for the ice hockey club Södertälje SK.
  • B. SKN
    SKN is the station code for South Kensington tube station, a major London Underground interchange serving the South Kensington area.
  • C. Skamneli
    Skamneli is a traditional mountain village in the Zagori region of Epirus, northwestern Greece, known for its stone-built architecture and scenic natural surroundings.
  • D. Schney
    Schney is a district or locality within the town of Lichtenfels in the Upper Franconia region of Bavaria, Germany.
  • E. Skjåk
    Skjåk is a rural municipality in Innlandet county, Norway, known for its mountainous landscapes, national parks, and dry inland climate.
  • 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_69bd441721cc819085c7e33fe0876818 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd70a8e5388190882831d7828441d3 completed March 20, 2026, 4:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69be77c6566c8190b0c76c05b9d82053 completed March 21, 2026, 10:49 a.m.
NEDg Description generation batch_69be78ac2d888190b53d90452431263f completed March 21, 2026, 10:53 a.m.
NED2 Entity disambiguation (via description) batch_69be79a6634c8190bae1fa09eedd6829 completed March 21, 2026, 10:57 a.m.
Created at: March 20, 2026, 1:31 p.m.