Triple

T7760873
Position Surface form Disambiguated ID Type / Status
Subject House of Lorraine E176016 entity
Predicate hasMainTitle P20947 FINISHED
Object Count of Marsan
The Count of Marsan was a noble title historically associated with a cadet branch of the influential House of Lorraine in France.
E686944 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: Count of Marsan | Statement: [House of Lorraine, hasMainTitle, Count of Marsan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Count of Marsan
Context triple: [House of Lorraine, hasMainTitle, Count of Marsan]
  • A. Marsan
    Marsan is a small rural settlement located within the Qakh District of Azerbaijan.
  • B. Mars of Todi
    Mars of Todi is a renowned life-size Etruscan bronze statue of a warrior, notable for its detailed armor and blend of Etruscan and classical Greek artistic influences.
  • C. Mars Gradivus
    Mars Gradivus is a martial aspect of the Roman god Mars, venerated as a fierce, battle-ready deity who strides into war at the head of armies.
  • D. Marsden
    Marsden is a village in West Yorkshire, England, situated in the Colne Valley near the Pennines and known for its industrial heritage and scenic moorland surroundings.
  • E. MARS
    MARS is a prominent benchmark suite used in computer architecture and systems research, often serving as a standard workload for evaluating and comparing processor and memory system performance.
  • 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: Count of Marsan
Triple: [House of Lorraine, hasMainTitle, Count of Marsan]
Generated description
The Count of Marsan was a noble title historically associated with a cadet branch of the influential House of Lorraine in France.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Count of Marsan
Target entity description: The Count of Marsan was a noble title historically associated with a cadet branch of the influential House of Lorraine in France.
  • A. Marsan
    Marsan is a small rural settlement located within the Qakh District of Azerbaijan.
  • B. Mars of Todi
    Mars of Todi is a renowned life-size Etruscan bronze statue of a warrior, notable for its detailed armor and blend of Etruscan and classical Greek artistic influences.
  • C. Mars Gradivus
    Mars Gradivus is a martial aspect of the Roman god Mars, venerated as a fierce, battle-ready deity who strides into war at the head of armies.
  • D. Marsden
    Marsden is a village in West Yorkshire, England, situated in the Colne Valley near the Pennines and known for its industrial heritage and scenic moorland surroundings.
  • E. MARS
    MARS is a prominent benchmark suite used in computer architecture and systems research, often serving as a standard workload for evaluating and comparing processor and memory system performance.
  • 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_69c69962923c8190ac74d28b4f9fe0a0 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c704036c588190a441e56c738cc309 completed March 27, 2026, 10:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8c7d2be488190bad1026b76fd0cd3 completed March 29, 2026, 6:33 a.m.
NEDg Description generation batch_69c8c855af8881908bad7f278c492877 completed March 29, 2026, 6:36 a.m.
NED2 Entity disambiguation (via description) batch_69c8c8c516048190957d937f2f2273ad completed March 29, 2026, 6:37 a.m.
Created at: March 27, 2026, 4:09 p.m.