Triple

T22415606
Position Surface form Disambiguated ID Type / Status
Subject Dintel E554115 entity
Predicate mouthLocatedNear P18935 FINISHED
Object Mark
Mark is a river in the southern Netherlands and northern Belgium that serves as a tributary of the Dintel and forms part of the region’s inland waterway network.
 E131045 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: Mark | Statement: [Dintel, mouthLocatedNear, Mark]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mark
Context triple: [Dintel, mouthLocatedNear, Mark]
  • A. Mark
    The Mark was the basic unit of currency used in Germany during various historical periods, including the era of the Papiermark.
  • B. Mark
    Mark is a quirky, music-obsessed employee at the independent record store in the 1995 cult film "Empire Records," known for his goofy charm and laid-back attitude.
  • C. Mark
    Mark is a musician known for being a member of the punk rock band The Groovie Ghoulies.
  • D. Mark
    Mark is the given name of Mark Boucher, a renowned South African cricketer and former wicket-keeper.
  • E. Mark
    Mark is a punctuation symbol used in writing systems, including those that employ the Cyrillic Extended-B Unicode block.
  • 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: Mark
Triple: [Dintel, mouthLocatedNear, Mark]
Generated description
Mark is a river in the southern Netherlands and northern Belgium that serves as a tributary of the Dintel and forms part of the region’s inland waterway network.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mark
Target entity description: Mark is a river in the southern Netherlands and northern Belgium that serves as a tributary of the Dintel and forms part of the region’s inland waterway network.
  • A. Mark chosen
    Mark is a river in the southern Netherlands and northern Belgium that flows through the province of North Brabant before joining the Dintel.
  • B. Mark
    Mark refers to the historic Margraviate of Brandenburg, a key principality of the Holy Roman Empire that later formed the core territory of Brandenburg-Prussia.
  • C. Mark
    Mark is a punctuation symbol used in writing systems, including those that employ the Cyrillic Extended-B Unicode block.
  • D. Mark
    The Mark was the basic unit of currency used in Germany during various historical periods, including the era of the Papiermark.
  • E. Mark
    Mark is the given name of Mark Boucher, a renowned South African cricketer and former wicket-keeper.
  • F. None of above.

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_69e11e4e6ce8819085a1e06d886bf21c completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1594615f881909688b02548ee83eb completed April 29, 2026, 1:05 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0af0e99ca48190ad93201035c819d6 completed May 18, 2026, 10:58 a.m.
NEDg Description generation batch_6a0af2c6151881908f85a7c3c751cea9 completed May 18, 2026, 11:06 a.m.
NED2 Entity disambiguation (via description) batch_6a0b08e411048190a368214c57c35d5e completed May 18, 2026, 12:41 p.m.
Created at: April 16, 2026, 8:46 p.m.