Triple

T9448099
Position Surface form Disambiguated ID Type / Status
Subject Port of Tangshan E227816 entity
Predicate UNLocode P1800 FINISHED
Object CNTSN
CNTSN is the UN/LOCODE identifier for the Port of Tangshan, a major Chinese seaport on the Bohai Sea serving industrial and bulk cargo traffic.
 E799500 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: CNTSN | Statement: [Port of Tangshan, UNLocode, CNTSN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: CNTSN
Context triple: [Port of Tangshan, UNLocode, CNTSN]
  • A. TSN1
    TSN1 is a Canadian English-language sports television channel operated by The Sports Network, featuring live sports coverage, analysis, and related programming.
  • B. CNT
    CNT is the commonly used abbreviation for the USA Baseball Collegiate National Team, which features top U.S. college baseball players in international competition.
  • C. CTN
    CTN is the ICAO airline designator used to identify Croatia Airlines in international aviation operations.
  • D. TNCS
    TNCS is the ICAO airport code for Juancho E. Yrausquin Airport, a small Caribbean airport on the Dutch island of Saba known for having one of the world’s shortest commercial runways.
  • E. CNK
    CNK is the stock ticker symbol for Cinemark Holdings, Inc., a major American movie theater chain operator.
  • 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: CNTSN
Triple: [Port of Tangshan, UNLocode, CNTSN]
Generated description
CNTSN is the UN/LOCODE identifier for the Port of Tangshan, a major Chinese seaport on the Bohai Sea serving industrial and bulk cargo traffic.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: CNTSN
Target entity description: CNTSN is the UN/LOCODE identifier for the Port of Tangshan, a major Chinese seaport on the Bohai Sea serving industrial and bulk cargo traffic.
  • A. TSN1
    TSN1 is a Canadian English-language sports television channel operated by The Sports Network, featuring live sports coverage, analysis, and related programming.
  • B. CNT
    CNT is the commonly used abbreviation for the USA Baseball Collegiate National Team, which features top U.S. college baseball players in international competition.
  • C. CTN
    CTN is the ICAO airline designator used to identify Croatia Airlines in international aviation operations.
  • D. TNCS
    TNCS is the ICAO airport code for Juancho E. Yrausquin Airport, a small Caribbean airport on the Dutch island of Saba known for having one of the world’s shortest commercial runways.
  • E. CNK
    CNK is the stock ticker symbol for Cinemark Holdings, Inc., a major American movie theater chain operator.
  • 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_69ca8439f8bc8190997f2ef40c9f0bc2 completed March 30, 2026, 2:10 p.m.
NER Named-entity recognition batch_69cd7f62dfa48190bf318777d97f0f2a completed April 1, 2026, 8:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1106aeb708190bbbe1d05b7472194 completed April 4, 2026, 1:21 p.m.
NEDg Description generation batch_69d111213e9081909865b086681d1bbd completed April 4, 2026, 1:24 p.m.
NED2 Entity disambiguation (via description) batch_69d111ab40a48190bb77c1cf80ef87a8 completed April 4, 2026, 1:27 p.m.
Created at: March 30, 2026, 7:51 p.m.