Triple
T13534761
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wards of the City of London |
E323231
|
entity |
| Predicate | hasSubdivision |
P747
|
FINISHED |
| Object |
Vintry
Vintry is one of the historic wards of the City of London, traditionally associated with the wine trade along the River Thames.
|
E1047636
|
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: Vintry | Statement: [Wards of the City of London, hasSubdivision, Vintry]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vintry Context triple: [Wards of the City of London, hasSubdivision, Vintry]
-
A.
YTS
YTS is the IATA airport code for Timmins Victor M. Power Airport, a regional airport serving the city of Timmins in Ontario, Canada.
-
B.
FilmFour
FilmFour is a British film production company and former television channel associated with Channel 4, known for backing distinctive independent and arthouse films.
-
C.
ArenaFilm
ArenaFilm is an Australian film production company known for producing the critically acclaimed drama "Romulus, My Father."
-
D.
FilmRise
FilmRise is an independent film and television distribution company known for acquiring and releasing a wide range of indie features, documentaries, and classic content across digital and traditional platforms.
-
E.
FilmBuff
FilmBuff was a digital film distribution company specializing in releasing independent and documentary films across online platforms.
- 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: Vintry Triple: [Wards of the City of London, hasSubdivision, Vintry]
Generated description
Vintry is one of the historic wards of the City of London, traditionally associated with the wine trade along the River Thames.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Vintry Target entity description: Vintry is one of the historic wards of the City of London, traditionally associated with the wine trade along the River Thames.
-
A.
YTS
YTS is the IATA airport code for Timmins Victor M. Power Airport, a regional airport serving the city of Timmins in Ontario, Canada.
-
B.
FilmFour
FilmFour is a British film production company and former television channel associated with Channel 4, known for backing distinctive independent and arthouse films.
-
C.
ArenaFilm
ArenaFilm is an Australian film production company known for producing the critically acclaimed drama "Romulus, My Father."
-
D.
FilmRise
FilmRise is an independent film and television distribution company known for acquiring and releasing a wide range of indie features, documentaries, and classic content across digital and traditional platforms.
-
E.
FilmBuff
FilmBuff was a digital film distribution company specializing in releasing independent and documentary films across online platforms.
- 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_69d8076776248190bdf0d4fa1f85a5fc |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbafbcad2881909fb7490311807f75 |
completed | April 12, 2026, 2:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f75d980cac8190a7f7fda56abda361 |
completed | May 3, 2026, 2:37 p.m. |
| NEDg | Description generation | batch_69f761d2a944819088965af57d5119a7 |
completed | May 3, 2026, 2:55 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f7624278388190a7edf96f7c298d2d |
completed | May 3, 2026, 2:57 p.m. |
Created at: April 9, 2026, 9:44 p.m.