Triple
T14654237
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kamarajar Port Limited |
E344067
|
entity |
| Predicate | hasAbbreviation |
P43
|
FINISHED |
| Object |
KPL
KPL is an Indian government-owned company that operates and manages Kamarajar Port, a major seaport near Chennai in Tamil Nadu.
|
E1112061
|
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: KPL | Statement: [Kamarajar Port Limited, hasAbbreviation, KPL]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: KPL Context triple: [Kamarajar Port Limited, hasAbbreviation, KPL]
-
A.
LPL
LPL is the three-letter IATA airport code for Liverpool John Lennon Airport, serving the city of Liverpool in England.
-
B.
LPL
LPL is the commonly used abbreviation for the Libyan Premier League, the top professional football league in Libya.
-
C.
C9 League
The C9 League is an elite alliance of nine top Chinese universities recognized for their leading roles in research, education, and academic excellence.
-
D.
LCK
LCK is the IATA airport code for Rickenbacker International Airport, a cargo-focused and passenger-supporting airport serving the Columbus, Ohio area.
-
E.
Proleague
Proleague was a premier professional team-based esports league in South Korea, best known for its highly competitive StarCraft: Brood War matches and influential role in shaping early esports culture.
- 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: KPL Triple: [Kamarajar Port Limited, hasAbbreviation, KPL]
Generated description
KPL is an Indian government-owned company that operates and manages Kamarajar Port, a major seaport near Chennai in Tamil Nadu.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: KPL Target entity description: KPL is an Indian government-owned company that operates and manages Kamarajar Port, a major seaport near Chennai in Tamil Nadu.
-
A.
LPL
LPL is the three-letter IATA airport code for Liverpool John Lennon Airport, serving the city of Liverpool in England.
-
B.
LPL
LPL is the commonly used abbreviation for the Libyan Premier League, the top professional football league in Libya.
-
C.
C9 League
The C9 League is an elite alliance of nine top Chinese universities recognized for their leading roles in research, education, and academic excellence.
-
D.
LCK
LCK is the IATA airport code for Rickenbacker International Airport, a cargo-focused and passenger-supporting airport serving the Columbus, Ohio area.
-
E.
Proleague
Proleague was a premier professional team-based esports league in South Korea, best known for its highly competitive StarCraft: Brood War matches and influential role in shaping early esports culture.
- 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_69d822e1a2cc81908e5bb93cf61ce3cc |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb518f7dc8190877997ea4cd3eed2 |
completed | April 14, 2026, 9:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fdd5db85648190b0e5b1c0827fa9f4 |
completed | May 8, 2026, 12:23 p.m. |
| NEDg | Description generation | batch_69fdd6ed699c8190919677dcdf2d24d9 |
completed | May 8, 2026, 12:28 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69fdd79198108190a3e640eca97b082b |
completed | May 8, 2026, 12:31 p.m. |
Created at: April 10, 2026, 1:27 a.m.