Triple
T10362887
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Institut Ramon Llull |
E244179
|
entity |
| Predicate | shortName |
P43
|
FINISHED |
| Object |
IRL
IRL is the acronym for Institut Ramon Llull, a public institution dedicated to promoting Catalan language and culture internationally.
|
E858047
|
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: IRL | Statement: [Institut Ramon Llull, shortName, IRL]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: IRL Context triple: [Institut Ramon Llull, shortName, IRL]
-
A.
IRL
IRL is the former name and common abbreviation for the Indy Racing League, the American open-wheel racing series now known as the IndyCar Series.
-
B.
IRL
IRL is the FIFA country code used to represent the Republic of Ireland national football team in international competitions and official records.
-
C.
IRL
IRL is the National Rail station code for Irlam railway station in Greater Manchester, England.
-
D.
IRL
IRL is the commonly used abbreviation for International Rugby League, the global governing body for the sport of rugby league.
-
E.
In real life
In real life is a major exhibition by artist Olafur Eliasson that immerses viewers in large-scale installations exploring perception, climate, and the relationship between humans and their environment.
- 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: IRL Triple: [Institut Ramon Llull, shortName, IRL]
Generated description
IRL is the acronym for Institut Ramon Llull, a public institution dedicated to promoting Catalan language and culture internationally.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: IRL Target entity description: IRL is the acronym for Institut Ramon Llull, a public institution dedicated to promoting Catalan language and culture internationally.
-
A.
IRL
IRL is the former name and common abbreviation for the Indy Racing League, the American open-wheel racing series now known as the IndyCar Series.
-
B.
IRL
IRL is the FIFA country code used to represent the Republic of Ireland national football team in international competitions and official records.
-
C.
IRL
IRL is the National Rail station code for Irlam railway station in Greater Manchester, England.
-
D.
IRL
IRL is the commonly used abbreviation for International Rugby League, the global governing body for the sport of rugby league.
-
E.
In real life
In real life is a major exhibition by artist Olafur Eliasson that immerses viewers in large-scale installations exploring perception, climate, and the relationship between humans and their environment.
- 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_69d381b3e328819094b23b8edcd29b5a |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e962f08c8190a7ac489dc524510d |
completed | April 7, 2026, 11:24 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d750bcf00081909b44ffa5df76aec1 |
completed | April 9, 2026, 7:09 a.m. |
| NEDg | Description generation | batch_69d7618fac288190a5da7549e5ccbdf0 |
completed | April 9, 2026, 8:21 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d77060331c8190a773a5f9ffadf1d6 |
completed | April 9, 2026, 9:24 a.m. |
Created at: April 6, 2026, noon