Triple

T7010663
Position Surface form Disambiguated ID Type / Status
Subject Port of Port-au-Prince E162570 entity
Predicate UNLOCODE P1800 FINISHED
Object HTPAP
HTPAP is the UN/LOCODE identifier for the Port of Port-au-Prince, the principal seaport serving Haiti’s capital city.
 E634823 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: HTPAP | Statement: [Port of Port-au-Prince, UNLOCODE, HTPAP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: HTPAP
Context triple: [Port of Port-au-Prince, UNLOCODE, HTPAP]
  • A. HAP
    HAP is Apple's HomeKit Accessory Protocol, a communication standard that defines how smart home accessories securely interact with Apple devices and the Home app.
  • B. Hpapun
    Hpapun is a major town in eastern Myanmar known for its location in the mountainous, conflict-affected region of Karen State.
  • C. HPA
    HPA is the commonly used abbreviation for the Horse Protection Act, a U.S. federal law aimed at preventing the abusive practice of soring in show horses.
  • D. HARP
    HARP is a submillimetre heterodyne array receiver used on the James Clerk Maxwell Telescope for high-resolution spectral observations of cold gas in space.
  • E. TPA
    TPA is an abbreviation commonly used for a Tri-Party Agreement, a legal contract involving three separate parties that defines their respective rights and obligations.
  • 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: HTPAP
Triple: [Port of Port-au-Prince, UNLOCODE, HTPAP]
Generated description
HTPAP is the UN/LOCODE identifier for the Port of Port-au-Prince, the principal seaport serving Haiti’s capital city.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: HTPAP
Target entity description: HTPAP is the UN/LOCODE identifier for the Port of Port-au-Prince, the principal seaport serving Haiti’s capital city.
  • A. HAP
    HAP is Apple's HomeKit Accessory Protocol, a communication standard that defines how smart home accessories securely interact with Apple devices and the Home app.
  • B. Hpapun
    Hpapun is a major town in eastern Myanmar known for its location in the mountainous, conflict-affected region of Karen State.
  • C. HPA
    HPA is the commonly used abbreviation for the Horse Protection Act, a U.S. federal law aimed at preventing the abusive practice of soring in show horses.
  • D. HARP
    HARP is a submillimetre heterodyne array receiver used on the James Clerk Maxwell Telescope for high-resolution spectral observations of cold gas in space.
  • E. TPA
    TPA is an abbreviation commonly used for a Tri-Party Agreement, a legal contract involving three separate parties that defines their respective rights and obligations.
  • 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_69c6885928148190ae31909fbb5e9849 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6dc3917c481909a288c3e56630c48 completed March 27, 2026, 7:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69c76a4bd424819097e1543ec59979ff completed March 28, 2026, 5:42 a.m.
NEDg Description generation batch_69c76b1ef6f481908f4c4f610328f633 completed March 28, 2026, 5:46 a.m.
NED2 Entity disambiguation (via description) batch_69c76c01679c8190b61f642c23c25ed5 completed March 28, 2026, 5:49 a.m.
Created at: March 27, 2026, 2:34 p.m.