Triple
T7427325
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Indian Super League |
E171400
|
entity |
| Predicate | mostTitlesClub |
P2660
|
FINISHED |
| Object |
ATK
ATK was a Kolkata-based professional football club that became one of the most successful teams in the Indian Super League before merging with Mohun Bagan.
|
E663639
|
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: ATK | Statement: [Indian Super League, mostTitlesClub, ATK]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ATK Context triple: [Indian Super League, mostTitlesClub, ATK]
-
A.
ATK
ATK is the stock ticker symbol for WS Atkins, a British multinational engineering and design consultancy firm.
-
B.
ATK
ATK is the IATA airport code for Atqasuk Edward Burnell Sr. Memorial Airport serving the village of Atqasuk in Alaska, United States.
-
C.
ATN
ATN most likely refers to Augmented Transition Network, a type of finite state machine used in computational linguistics and natural language processing for parsing sentences.
-
D.
ATF
ATF is a United States federal law enforcement agency responsible for regulating and investigating crimes involving alcohol, tobacco, firearms, explosives, and arson.
-
E.
ATZ
ATZ is the IATA airport code for Assiut Airport, a regional airport serving the city of Assiut in Egypt.
- 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: ATK Triple: [Indian Super League, mostTitlesClub, ATK]
Generated description
ATK was a Kolkata-based professional football club that became one of the most successful teams in the Indian Super League before merging with Mohun Bagan.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: ATK Target entity description: ATK was a Kolkata-based professional football club that became one of the most successful teams in the Indian Super League before merging with Mohun Bagan.
-
A.
ATK
ATK is the stock ticker symbol for WS Atkins, a British multinational engineering and design consultancy firm.
-
B.
ATK
ATK is the IATA airport code for Atqasuk Edward Burnell Sr. Memorial Airport serving the village of Atqasuk in Alaska, United States.
-
C.
ATN
ATN most likely refers to Augmented Transition Network, a type of finite state machine used in computational linguistics and natural language processing for parsing sentences.
-
D.
ATF
ATF is a United States federal law enforcement agency responsible for regulating and investigating crimes involving alcohol, tobacco, firearms, explosives, and arson.
-
E.
ATZ
ATZ is the IATA airport code for Assiut Airport, a regional airport serving the city of Assiut in Egypt.
- 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_69c68a63491881909281f73d4d5643bf |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f3055b7881908269ab909c5a85b5 |
completed | March 27, 2026, 9:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c81f0e28e88190805108dff740dda3 |
completed | March 28, 2026, 6:33 p.m. |
| NEDg | Description generation | batch_69c8200c52c8819083b14e8d768fc9be |
completed | March 28, 2026, 6:38 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c82084879c8190ae60b99f702dc058 |
completed | March 28, 2026, 6:40 p.m. |
Created at: March 27, 2026, 3:12 p.m.