Triple
T19424009
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | De Rotterdam |
E485932
|
entity |
| Predicate | developer |
P73
|
FINISHED |
| Object |
MAB Development
MAB Development is a Dutch real estate development company known for creating large-scale, architecturally prominent urban projects.
|
E1375597
|
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: MAB Development | Statement: [De Rotterdam, developer, MAB Development]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MAB Development Context triple: [De Rotterdam, developer, MAB Development]
-
A.
MAB
MAB is a German vehicle registration code used for cars registered in the Erzgebirgskreis district of Saxony.
-
B.
MAB
MAB is a German bibliographic data format used for cataloging and exchanging library records, closely related to and historically aligned with MARC standards.
-
C.
MAB
MAB is the London Stock Exchange ticker symbol for Mitchells & Butlers plc, a major UK operator of pubs, bars, and restaurants.
-
D.
MAB Engineering
MAB Engineering is the maintenance, repair, and overhaul (MRO) arm of Malaysia Aviation Group, providing engineering and technical support services for aircraft and aviation operations.
-
E.
MAB Academy
MAB Academy is the training and development arm of Malaysia Aviation Group, providing aviation-related education and professional courses for airline and aviation industry personnel.
- 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: MAB Development Triple: [De Rotterdam, developer, MAB Development]
Generated description
MAB Development is a Dutch real estate development company known for creating large-scale, architecturally prominent urban projects.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: MAB Development Target entity description: MAB Development is a Dutch real estate development company known for creating large-scale, architecturally prominent urban projects.
-
A.
MAB
MAB is a German bibliographic data format used for cataloging and exchanging library records, closely related to and historically aligned with MARC standards.
-
B.
MAB
MAB is a German vehicle registration code used for cars registered in the Erzgebirgskreis district of Saxony.
-
C.
MAB
MAB is the London Stock Exchange ticker symbol for Mitchells & Butlers plc, a major UK operator of pubs, bars, and restaurants.
-
D.
MAB Engineering
MAB Engineering is the maintenance, repair, and overhaul (MRO) arm of Malaysia Aviation Group, providing engineering and technical support services for aircraft and aviation operations.
-
E.
MAB Academy
MAB Academy is the training and development arm of Malaysia Aviation Group, providing aviation-related education and professional courses for airline and aviation industry personnel.
- 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_69d8e8d688f881909c85104a62e09d8a |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e632169d9c81909a88704c6beb8fe0 |
completed | April 20, 2026, 2:03 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0733d40a648190b934f5dfc7b5d44f |
completed | May 15, 2026, 2:55 p.m. |
| NEDg | Description generation | batch_6a07352d07a48190b29bfd46c7c93f30 |
completed | May 15, 2026, 3:01 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0735b445388190a588f6eeaf49e1b7 |
completed | May 15, 2026, 3:03 p.m. |
Created at: April 10, 2026, 1:37 p.m.