Triple
T663857
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kraków |
E12815
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object |
Cloth Hall
Cloth Hall is a historic Renaissance-era market hall in Kraków’s Main Square, long serving as a center of trade and one of the city’s most iconic architectural landmarks.
|
E83024
|
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: Cloth Hall | Statement: [Kraków, hasLandmark, Cloth Hall]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cloth Hall Context triple: [Kraków, hasLandmark, Cloth Hall]
-
A.
Mosaic Hall
Mosaic Hall was an ornate ceremonial chamber within the Reich Chancellery in Berlin, used for official receptions and state functions during the Nazi era.
-
B.
Canton Hall
Canton Hall is a historic live music and event venue located in Dallas’s Deep Ellum entertainment district.
-
C.
Kingdom Hall
Kingdom Hall is the name given to the local meeting places used by Jehovah’s Witnesses for their congregational worship and religious activities.
-
D.
White Hall
White Hall is a grand ceremonial room within the Livadia Palace, historically used for important receptions and diplomatic events.
-
E.
White Hall
White Hall is a historic academic building on Cornell University's central Arts Quad, known for housing classrooms and offices for humanities and social sciences.
- 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: Cloth Hall Triple: [Kraków, hasLandmark, Cloth Hall]
Generated description
Cloth Hall is a historic Renaissance-era market hall in Kraków’s Main Square, long serving as a center of trade and one of the city’s most iconic architectural landmarks.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Cloth Hall Target entity description: Cloth Hall is a historic Renaissance-era market hall in Kraków’s Main Square, long serving as a center of trade and one of the city’s most iconic architectural landmarks.
-
A.
Mosaic Hall
Mosaic Hall was an ornate ceremonial chamber within the Reich Chancellery in Berlin, used for official receptions and state functions during the Nazi era.
-
B.
Canton Hall
Canton Hall is a historic live music and event venue located in Dallas’s Deep Ellum entertainment district.
-
C.
Kingdom Hall
Kingdom Hall is the name given to the local meeting places used by Jehovah’s Witnesses for their congregational worship and religious activities.
-
D.
White Hall
White Hall is a grand ceremonial room within the Livadia Palace, historically used for important receptions and diplomatic events.
-
E.
White Hall
White Hall is a historic academic building on Cornell University's central Arts Quad, known for housing classrooms and offices for humanities and social sciences.
- 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_69a493355dec819098d4244b2fa34885 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49fd1f0ec819087003d30bbab2fa6 |
completed | March 1, 2026, 8:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a5c398cc748190ab720263096064ef |
completed | March 2, 2026, 5:06 p.m. |
| NEDg | Description generation | batch_69a5c4523e8081909464ca227b880e77 |
completed | March 2, 2026, 5:09 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69a5cdae65808190b7191f63d5f16d9f |
completed | March 2, 2026, 5:49 p.m. |
Created at: March 1, 2026, 7:36 p.m.