Triple
T23168249
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Libbey Glass |
E578771
|
entity |
| Predicate | hasSubsidiary |
P254
|
FINISHED |
| Object |
Royal Leerdam
Royal Leerdam is a historic Dutch glassware manufacturer renowned for its high-quality crystal and design-driven table glass.
|
E1572023
|
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: Royal Leerdam | Statement: [Libbey Glass, hasSubsidiary, Royal Leerdam]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Royal Leerdam Context triple: [Libbey Glass, hasSubsidiary, Royal Leerdam]
-
A.
Reinaert
Reinaert is the Dutch name for Reynard, the cunning anthropomorphic fox who is the central trickster figure of a long-standing European cycle of beast fables.
-
B.
Beerzelberg
Beerzelberg is a modest hill in Belgium known as the highest natural point in Antwerp Province.
-
C.
Royal Tichelaar Makkum
Royal Tichelaar Makkum is a historic Dutch ceramics manufacturer renowned for its traditional and contemporary earthenware and tile production.
-
D.
Ros Beiaard
Ros Beiaard is a legendary giant horse from Flemish folklore, famously celebrated in the decennial Ros Beiaard procession in Dendermonde, Belgium.
-
E.
Lammbock
Lammbock is a German stoner comedy film that follows two friends running a pizza delivery service as a front for their marijuana business.
- 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: Royal Leerdam Triple: [Libbey Glass, hasSubsidiary, Royal Leerdam]
Generated description
Royal Leerdam is a historic Dutch glassware manufacturer renowned for its high-quality crystal and design-driven table glass.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Royal Leerdam Target entity description: Royal Leerdam is a historic Dutch glassware manufacturer renowned for its high-quality crystal and design-driven table glass.
-
A.
Reinaert
Reinaert is the Dutch name for Reynard, the cunning anthropomorphic fox who is the central trickster figure of a long-standing European cycle of beast fables.
-
B.
Beerzelberg
Beerzelberg is a modest hill in Belgium known as the highest natural point in Antwerp Province.
-
C.
Royal Tichelaar Makkum
Royal Tichelaar Makkum is a historic Dutch ceramics manufacturer renowned for its traditional and contemporary earthenware and tile production.
-
D.
Ros Beiaard
Ros Beiaard is a legendary giant horse from Flemish folklore, famously celebrated in the decennial Ros Beiaard procession in Dendermonde, Belgium.
-
E.
Lammbock
Lammbock is a German stoner comedy film that follows two friends running a pizza delivery service as a front for their marijuana business.
- 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_69e245fc75348190a0288401044c8af8 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18f2d51288190af0d5747090d8e5d |
completed | April 29, 2026, 4:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c30a88f5481909885c05b189f71a6 |
completed | May 19, 2026, 9:43 a.m. |
| NEDg | Description generation | batch_6a0c312da45881908330ce9d0c8795b9 |
completed | May 19, 2026, 9:45 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c31a2ce1881909bc4584a1ae7bcdc |
completed | May 19, 2026, 9:47 a.m. |
Created at: April 17, 2026, 4:03 p.m.