Triple

T16826837
Position Surface form Disambiguated ID Type / Status
Subject Ned Martin E409039 entity
Predicate employer P7 FINISHED
Object WPLM
WPLM is a radio station based in Plymouth, Massachusetts, known for its adult contemporary and soft rock programming.
 E1234708 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: WPLM | Statement: [Ned Martin, employer, WPLM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: WPLM
Context triple: [Ned Martin, employer, WPLM]
  • A. WZLX
    WZLX is a Boston-based FM radio station best known for its classic rock format and long-standing presence in the city’s radio market.
  • B. WAPP-FM
    WAPP-FM was a New York City FM radio station best known in the early 1980s for its rock format and for helping launch the career of Jon Bon Jovi with the song "Runaway."
  • C. WPLG
    WPLG is a television station serving the Miami–Fort Lauderdale market, best known as the local ABC network affiliate.
  • D. WMKL
    WMKL is the ICAO airport code for Langkawi International Airport in Malaysia, which serves the island of Langkawi as its main air gateway.
  • E. WZPT
    WZPT is a Pittsburgh, Pennsylvania FM radio station branded as "96.1 KISS" that features a contemporary hit music format.
  • 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: WPLM
Triple: [Ned Martin, employer, WPLM]
Generated description
WPLM is a radio station based in Plymouth, Massachusetts, known for its adult contemporary and soft rock programming.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: WPLM
Target entity description: WPLM is a radio station based in Plymouth, Massachusetts, known for its adult contemporary and soft rock programming.
  • A. WZLX
    WZLX is a Boston-based FM radio station best known for its classic rock format and long-standing presence in the city’s radio market.
  • B. WAPP-FM
    WAPP-FM was a New York City FM radio station best known in the early 1980s for its rock format and for helping launch the career of Jon Bon Jovi with the song "Runaway."
  • C. WPLG
    WPLG is a television station serving the Miami–Fort Lauderdale market, best known as the local ABC network affiliate.
  • D. WMKL
    WMKL is the ICAO airport code for Langkawi International Airport in Malaysia, which serves the island of Langkawi as its main air gateway.
  • E. WZPT
    WZPT is a Pittsburgh, Pennsylvania FM radio station branded as "96.1 KISS" that features a contemporary hit music format.
  • 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_69d88394566c8190b3dcbdc72935f7fa completed April 10, 2026, 4:59 a.m.
NER Named-entity recognition batch_69e3b31404c88190a3b2802842ca77eb completed April 18, 2026, 4:36 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00b29e48f881908489bd77a9caec97 completed May 10, 2026, 4:30 p.m.
NEDg Description generation batch_6a00b3aafac08190b3e0181780f45392 completed May 10, 2026, 4:34 p.m.
NED2 Entity disambiguation (via description) batch_6a00b46ab0608190bc59abb99842e6d4 completed May 10, 2026, 4:38 p.m.
Created at: April 10, 2026, 5:23 a.m.