Triple
T13449257
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Broel Towers |
E320565
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object |
Speyetoren
Speyetoren is one of the historic medieval Broel Towers in Kortrijk, Belgium, notable as a remnant of the city’s former fortifications.
|
E1040291
|
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: Speyetoren | Statement: [Broel Towers, hasPart, Speyetoren]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Speyetoren Context triple: [Broel Towers, hasPart, Speyetoren]
-
A.
Messeturm
Messeturm is a prominent postmodern skyscraper in Frankfurt, Germany, known as one of the city's tallest and most recognizable landmarks.
-
B.
Munttoren
Munttoren is a historic clock and bell tower in central Amsterdam, originally part of the city’s medieval fortifications and now a notable canal-side landmark.
-
C.
Wachtturm
Wachtturm is one of the historic defensive towers incorporated into Lucerne’s medieval Musegg Wall fortifications in Switzerland.
-
D.
Falterturm
Falterturm is a distinctive historic tower in the Bavarian town of Kitzingen, known for its leaning structure and role as a former watchtower.
-
E.
Vision Tower
Vision Tower is a prominent commercial skyscraper in Dubai known for its distinctive modern architecture and prime location in the Business Bay district.
- 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: Speyetoren Triple: [Broel Towers, hasPart, Speyetoren]
Generated description
Speyetoren is one of the historic medieval Broel Towers in Kortrijk, Belgium, notable as a remnant of the city’s former fortifications.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Speyetoren Target entity description: Speyetoren is one of the historic medieval Broel Towers in Kortrijk, Belgium, notable as a remnant of the city’s former fortifications.
-
A.
Messeturm
Messeturm is a prominent postmodern skyscraper in Frankfurt, Germany, known as one of the city's tallest and most recognizable landmarks.
-
B.
Munttoren
Munttoren is a historic clock and bell tower in central Amsterdam, originally part of the city’s medieval fortifications and now a notable canal-side landmark.
-
C.
Wachtturm
Wachtturm is one of the historic defensive towers incorporated into Lucerne’s medieval Musegg Wall fortifications in Switzerland.
-
D.
Falterturm
Falterturm is a distinctive historic tower in the Bavarian town of Kitzingen, known for its leaning structure and role as a former watchtower.
-
E.
Vision Tower
Vision Tower is a prominent commercial skyscraper in Dubai known for its distinctive modern architecture and prime location in the Business Bay district.
- 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_69d80761e6cc8190a90c844589998ecc |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbaef758b08190b9aa5ec7082cd417 |
completed | April 12, 2026, 2:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f73999f8388190b2c578e063341178 |
completed | May 3, 2026, 12:03 p.m. |
| NEDg | Description generation | batch_69f73af2b37481908c4d282c1335fe08 |
completed | May 3, 2026, 12:09 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f73b959de88190959335353242031b |
completed | May 3, 2026, 12:12 p.m. |
Created at: April 9, 2026, 9:41 p.m.