Triple
T11789484
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Israeli lira |
E280352
|
entity |
| Predicate | ISO4217Code |
P189
|
FINISHED |
| Object |
ILR
ILR was the former ISO 4217 currency code for the Israeli lira, the currency used in Israel before the adoption of the shekel.
|
E946582
|
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: ILR | Statement: [Israeli lira, ISO4217Code, ILR]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ILR Context triple: [Israeli lira, ISO4217Code, ILR]
-
A.
ILR
ILR is the IATA airport code for Ilorin International Airport serving the city of Ilorin in Nigeria.
-
B.
HIRS
HIRS (High-resolution Infrared Radiation Sounder) is a satellite-borne infrared radiometer used on Polar Operational Environmental Satellites to measure atmospheric temperature and humidity profiles for weather forecasting and climate monitoring.
-
C.
HILR
HILR is a Harvard-affiliated institute that offers peer-led, lifelong learning opportunities for retired and semi-retired adults.
-
D.
IRM
IRM is a theological and missiological academic journal focusing on global Christian mission studies and practice.
-
E.
IRM
IRM is a 2009 experimental pop album by Charlotte Gainsbourg, produced and largely written by Beck, noted for its introspective themes and eclectic sound.
- 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: ILR Triple: [Israeli lira, ISO4217Code, ILR]
Generated description
ILR was the former ISO 4217 currency code for the Israeli lira, the currency used in Israel before the adoption of the shekel.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: ILR Target entity description: ILR was the former ISO 4217 currency code for the Israeli lira, the currency used in Israel before the adoption of the shekel.
-
A.
ILR
ILR is the IATA airport code for Ilorin International Airport serving the city of Ilorin in Nigeria.
-
B.
HIRS
HIRS (High-resolution Infrared Radiation Sounder) is a satellite-borne infrared radiometer used on Polar Operational Environmental Satellites to measure atmospheric temperature and humidity profiles for weather forecasting and climate monitoring.
-
C.
HILR
HILR is a Harvard-affiliated institute that offers peer-led, lifelong learning opportunities for retired and semi-retired adults.
-
D.
IRM
IRM is a theological and missiological academic journal focusing on global Christian mission studies and practice.
-
E.
IRM
IRM is a 2009 experimental pop album by Charlotte Gainsbourg, produced and largely written by Beck, noted for its introspective themes and eclectic sound.
- 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_69d6ab258b808190b1735835c841e3a4 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a587c2d881909297c3a6c7d26080 |
completed | April 10, 2026, 7:23 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f090f62bdc8190a8fd145839aef554 |
completed | April 28, 2026, 10:50 a.m. |
| NEDg | Description generation | batch_69f0bd3f39608190b29027b30664bd9c |
completed | April 28, 2026, 1:59 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f0ef5afd448190953b5d9929478132 |
completed | April 28, 2026, 5:33 p.m. |
Created at: April 8, 2026, 9:42 p.m.