Triple
T4778028
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | City of Holland, Michigan |
E106099
|
entity |
| Predicate | hasNickname |
P39
|
FINISHED |
| Object |
Tulip City
Tulip City is the nickname of Holland, Michigan, a city famed for its Dutch heritage and vibrant annual tulip festival.
|
E124499
|
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: Tulip City | Statement: [City of Holland, Michigan, hasNickname, Tulip City]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tulip City Context triple: [City of Holland, Michigan, hasNickname, Tulip City]
-
A.
City of Holland
The City of Holland is a Michigan community known for its Dutch heritage, tulip festivals, and attractions like historic windmills and themed gardens.
-
B.
Lichtstad
Lichtstad is the Dutch nickname for the city of Eindhoven, reflecting its historic association with the lighting industry and companies like Philips.
-
C.
Thienhoven
Thienhoven was one of the ships in the early 18th-century Dutch expedition led by explorer Jacob Roggeveen during his voyage across the Pacific.
-
D.
Wilrijk
Wilrijk is a southern district of the Belgian city of Antwerp, known for its residential character and green spaces.
-
E.
Windmill City
Windmill City is a nickname for Batavia, Illinois, reflecting its historic association with windmill manufacturing and numerous preserved windmills.
- 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: Tulip City Triple: [City of Holland, Michigan, hasNickname, Tulip City]
Generated description
Tulip City is the nickname of Holland, Michigan, a city famed for its Dutch heritage and vibrant annual tulip festival.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tulip City Target entity description: Tulip City is the nickname of Holland, Michigan, a city famed for its Dutch heritage and vibrant annual tulip festival.
-
A.
City of Holland
chosen
The City of Holland is a Michigan community known for its Dutch heritage, tulip festivals, and attractions like historic windmills and themed gardens.
-
B.
Lichtstad
Lichtstad is the Dutch nickname for the city of Eindhoven, reflecting its historic association with the lighting industry and companies like Philips.
-
C.
Thienhoven
Thienhoven was one of the ships in the early 18th-century Dutch expedition led by explorer Jacob Roggeveen during his voyage across the Pacific.
-
D.
Wilrijk
Wilrijk is a southern district of the Belgian city of Antwerp, known for its residential character and green spaces.
-
E.
Windmill City
Windmill City is a nickname for Batavia, Illinois, reflecting its historic association with windmill manufacturing and numerous preserved windmills.
- F. None of above.
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_69bd43f3074c8190937e7b0a457fe9f1 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd658942e481908570cfec77fe4a4b |
completed | March 20, 2026, 3:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be43caec588190880c47f11d3f2daf |
completed | March 21, 2026, 7:07 a.m. |
| NEDg | Description generation | batch_69be44df4e808190bb65ea205446a98f |
completed | March 21, 2026, 7:12 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69be45bc7b2c8190aa293d2c10077864 |
completed | March 21, 2026, 7:16 a.m. |
Created at: March 20, 2026, 1:21 p.m.