Triple
T6986772
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Soekarno–Hatta International Airport |
E161983
|
entity |
| Predicate | ICAOcode |
P419
|
FINISHED |
| Object |
WIII
WIII is the ICAO airport code for Soekarno–Hatta International Airport, the main international gateway serving Jakarta, Indonesia.
|
E633400
|
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: WIII | Statement: [Soekarno–Hatta International Airport, ICAOcode, WIII]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: WIII Context triple: [Soekarno–Hatta International Airport, ICAOcode, WIII]
-
A.
WIQ
WIQ is the National Rail station code for West India Quay Docklands Light Railway station in London.
-
B.
WMMR
WMMR is a long-running rock radio station based in Philadelphia, Pennsylvania, known for its influential role in album-oriented rock and local music culture.
-
C.
WATH
WATH is a local radio station serving the Athens, Ohio area with news, talk, and music programming.
-
D.
WIP-FM
WIP-FM is a Philadelphia-based sports radio station known for its live coverage of local teams and sports talk programming.
-
E.
WTW
WTW is the abbreviation for "Walking Together on the Way," an ecumenical document focused on fostering unity and dialogue among Christian traditions.
- 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: WIII Triple: [Soekarno–Hatta International Airport, ICAOcode, WIII]
Generated description
WIII is the ICAO airport code for Soekarno–Hatta International Airport, the main international gateway serving Jakarta, Indonesia.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: WIII Target entity description: WIII is the ICAO airport code for Soekarno–Hatta International Airport, the main international gateway serving Jakarta, Indonesia.
-
A.
WIQ
WIQ is the National Rail station code for West India Quay Docklands Light Railway station in London.
-
B.
WMMR
WMMR is a long-running rock radio station based in Philadelphia, Pennsylvania, known for its influential role in album-oriented rock and local music culture.
-
C.
WATH
WATH is a local radio station serving the Athens, Ohio area with news, talk, and music programming.
-
D.
WIP-FM
WIP-FM is a Philadelphia-based sports radio station known for its live coverage of local teams and sports talk programming.
-
E.
WTW
WTW is the abbreviation for "Walking Together on the Way," an ecumenical document focused on fostering unity and dialogue among Christian traditions.
- 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_69c68856d7808190ab33ee914640281b |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6db93c0ac8190a752a633247bb439 |
completed | March 27, 2026, 7:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c761cfda14819088e11889f0151a37 |
completed | March 28, 2026, 5:06 a.m. |
| NEDg | Description generation | batch_69c7630440508190a66f218fd912d732 |
completed | March 28, 2026, 5:11 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c7639747b88190b3429817d53c5703 |
completed | March 28, 2026, 5:13 a.m. |
Created at: March 27, 2026, 2:32 p.m.