Triple

T4931801
Position Surface form Disambiguated ID Type / Status
Subject Rhondda Valley E110712 entity
Predicate containsSettlement P847 FINISHED
Object Gelli
Gelli is a village in the Rhondda Valley of South Wales, historically associated with coal mining and the broader industrial heritage of the region.
 E480630 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: Gelli | Statement: [Rhondda Valley, containsSettlement, Gelli]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gelli
Context triple: [Rhondda Valley, containsSettlement, Gelli]
  • A. Gelo
    Gelo is a film featuring Spanish actress Ivana Baquero in a prominent role.
  • B. Gillam
    Gillam is a small remote community in northern Manitoba, Canada, known as a service and access point for nearby wilderness areas and hydroelectric developments.
  • C. Guilly
    Guilly is a small commune in the Loiret department of north-central France.
  • D. Golo
    Golo is a masculine given name most notably borne by the German historian and essayist Golo Mann.
  • E. Gooigi
    Gooigi is a green, goo-like doppelgänger of Luigi from the Luigi’s Mansion series, used as a playable helper character to solve puzzles and reach otherwise inaccessible areas.
  • 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: Gelli
Triple: [Rhondda Valley, containsSettlement, Gelli]
Generated description
Gelli is a village in the Rhondda Valley of South Wales, historically associated with coal mining and the broader industrial heritage of the region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Gelli
Target entity description: Gelli is a village in the Rhondda Valley of South Wales, historically associated with coal mining and the broader industrial heritage of the region.
  • A. Gelo
    Gelo is a film featuring Spanish actress Ivana Baquero in a prominent role.
  • B. Gillam
    Gillam is a small remote community in northern Manitoba, Canada, known as a service and access point for nearby wilderness areas and hydroelectric developments.
  • C. Guilly
    Guilly is a small commune in the Loiret department of north-central France.
  • D. Golo
    Golo is a masculine given name most notably borne by the German historian and essayist Golo Mann.
  • E. Gooigi
    Gooigi is a green, goo-like doppelgänger of Luigi from the Luigi’s Mansion series, used as a playable helper character to solve puzzles and reach otherwise inaccessible areas.
  • 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_69bd4415190c8190817bee7ec9f9f944 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd7063c57c8190a5a6fb3586238d35 completed March 20, 2026, 4:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69be77b18b6c8190bbc8d0764f6a03bf completed March 21, 2026, 10:49 a.m.
NEDg Description generation batch_69be78ce97948190a0a54b1baa0ff979 completed March 21, 2026, 10:54 a.m.
NED2 Entity disambiguation (via description) batch_69be7929cec08190a6fb28385c5bfce9 completed March 21, 2026, 10:55 a.m.
Created at: March 20, 2026, 1:30 p.m.