Triple
T8091010
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mainz |
E188859
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object |
Iron Tower
The Iron Tower is a historic medieval watchtower and former city gate located in Mainz, Germany.
|
E710594
|
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: Iron Tower | Statement: [Mainz, hasLandmark, Iron Tower]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Iron Tower Context triple: [Mainz, hasLandmark, Iron Tower]
-
A.
Eiffel Tower
The Eiffel Tower is a wrought-iron lattice tower in Paris, France, and one of the most recognizable landmarks and symbols of the country.
-
B.
Eiffel
Eiffel is a French surname most famously associated with engineer Gustave Eiffel, designer of the Eiffel Tower in Paris.
-
C.
Eiffel
Eiffel is an object-oriented programming language designed by Bertrand Meyer, known for its emphasis on software correctness through the Design by Contract methodology.
-
D.
Fourvière Metal Tower
The Fourvière Metal Tower is a prominent steel structure in Lyon, France, resembling a small Eiffel Tower and serving as a key telecommunications and skyline landmark.
-
E.
58 Tour Eiffel
58 Tour Eiffel is a contemporary French restaurant located on the first floor of the Eiffel Tower, offering panoramic views of Paris.
- 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: Iron Tower Triple: [Mainz, hasLandmark, Iron Tower]
Generated description
The Iron Tower is a historic medieval watchtower and former city gate located in Mainz, Germany.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Iron Tower Target entity description: The Iron Tower is a historic medieval watchtower and former city gate located in Mainz, Germany.
-
A.
Eiffel Tower
The Eiffel Tower is a wrought-iron lattice tower in Paris, France, and one of the most recognizable landmarks and symbols of the country.
-
B.
Eiffel
Eiffel is a French surname most famously associated with engineer Gustave Eiffel, designer of the Eiffel Tower in Paris.
-
C.
Eiffel
Eiffel is an object-oriented programming language designed by Bertrand Meyer, known for its emphasis on software correctness through the Design by Contract methodology.
-
D.
Fourvière Metal Tower
The Fourvière Metal Tower is a prominent steel structure in Lyon, France, resembling a small Eiffel Tower and serving as a key telecommunications and skyline landmark.
-
E.
58 Tour Eiffel
58 Tour Eiffel is a contemporary French restaurant located on the first floor of the Eiffel Tower, offering panoramic views of Paris.
- 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_69ca82b7b3e88190b9041ab0ef28b3cb |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb421fb8348190b6495394d498d3f4 |
completed | March 31, 2026, 3:40 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc640dbab881908a8142ac472f3408 |
completed | April 1, 2026, 12:17 a.m. |
| NEDg | Description generation | batch_69cc651e3b4c81908408c9f08eca8e09 |
completed | April 1, 2026, 12:21 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69cc69531a3c8190b712b3df6beefb7b |
completed | April 1, 2026, 12:39 a.m. |
Created at: March 30, 2026, 5:29 p.m.