Triple

T23015735
Position Surface form Disambiguated ID Type / Status
Subject Physicians for Human Rights E573025 entity
Predicate hasAbbreviation P43 FINISHED
Object PHR
PHR is an international non-governmental organization that uses medical and scientific expertise to investigate and document human rights violations and advocate for justice and accountability.
E1566592 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: PHR | Statement: [Physicians for Human Rights, hasAbbreviation, PHR]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: PHR
Context triple: [Physicians for Human Rights, hasAbbreviation, PHR]
  • A. LPHR
    LPHR is the ICAO airport code for Horta Airport, a regional airport serving the island of Faial in the Azores, Portugal.
  • B. PHN
    PHN is the IATA airport code for St. Clair County International Airport in Michigan, United States.
  • C. PHC
    PHC is the IATA airport code for Port Harcourt International Airport in Rivers State, Nigeria.
  • D. PHC
    PHC is the commonly used abbreviation for the Patna High Court, the high court of the Indian state of Bihar.
  • E. PH
    PH is the ISO 3166 country code for the Philippines, a Southeast Asian archipelagic nation in the western Pacific Ocean.
  • 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: PHR
Triple: [Physicians for Human Rights, hasAbbreviation, PHR]
Generated description
PHR is an international non-governmental organization that uses medical and scientific expertise to investigate and document human rights violations and advocate for justice and accountability.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: PHR
Target entity description: PHR is an international non-governmental organization that uses medical and scientific expertise to investigate and document human rights violations and advocate for justice and accountability.
  • A. LPHR
    LPHR is the ICAO airport code for Horta Airport, a regional airport serving the island of Faial in the Azores, Portugal.
  • B. PHN
    PHN is the IATA airport code for St. Clair County International Airport in Michigan, United States.
  • C. PHC
    PHC is the IATA airport code for Port Harcourt International Airport in Rivers State, Nigeria.
  • D. PHC
    PHC is the commonly used abbreviation for the Patna High Court, the high court of the Indian state of Bihar.
  • E. PH
    PH is the vehicle registration code used on license plates for vehicles registered in Ploiești, Romania.
  • 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_69e245b764cc8190a51be76f1d9611e1 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f183e4dcd48190b2b1c2ab43205e41 completed April 29, 2026, 4:07 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0bf2aa402881908c2c69889dd1b38c completed May 19, 2026, 5:18 a.m.
NEDg Description generation batch_6a0bfb46958881909f2035f1d7eed94f completed May 19, 2026, 5:55 a.m.
NED2 Entity disambiguation (via description) batch_6a0bfbbb1b4c8190ba6b9c8042939b8c completed May 19, 2026, 5:57 a.m.
Created at: April 17, 2026, 3:51 p.m.