Triple
T11190194
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dragon Stairway |
E264776
|
entity |
| Predicate | hasSculpture |
P1572
|
FINISHED |
| Object |
El Drac
El Drac is a famous mosaic-covered dragon sculpture by Antoni Gaudí located in Barcelona’s Park Güell.
|
E910740
|
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: El Drac | Statement: [Dragon Stairway, hasSculpture, El Drac]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: El Drac Context triple: [Dragon Stairway, hasSculpture, El Drac]
-
A.
El Draque
El Draque is the Spanish nickname for Sir Francis Drake, the famed 16th-century English sea captain, privateer, and circumnavigator who raided Spanish possessions in the Americas.
-
B.
The Dragon
The Dragon is the legendary Chinese table tennis player Ma Long, widely regarded as one of the greatest and most dominant players in the sport’s history.
-
C.
The Dragon
"The Dragon" is a track from Vangelis's 1979 electronic music album "China," blending synthesizer-driven soundscapes with an evocative, atmospheric style.
-
D.
The Dragon
The Dragon is a renowned martial arts school known for its rigorous training and emphasis on traditional fighting techniques.
-
E.
Drakonera
Drakonera is a notable Greek island in the Ionian Sea, forming part of the Echinades archipelago off the western coast of mainland Greece.
- 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: El Drac Triple: [Dragon Stairway, hasSculpture, El Drac]
Generated description
El Drac is a famous mosaic-covered dragon sculpture by Antoni Gaudí located in Barcelona’s Park Güell.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: El Drac Target entity description: El Drac is a famous mosaic-covered dragon sculpture by Antoni Gaudí located in Barcelona’s Park Güell.
-
A.
El Draque
El Draque is the Spanish nickname for Sir Francis Drake, the famed 16th-century English sea captain, privateer, and circumnavigator who raided Spanish possessions in the Americas.
-
B.
The Dragon
The Dragon is the legendary Chinese table tennis player Ma Long, widely regarded as one of the greatest and most dominant players in the sport’s history.
-
C.
The Dragon
"The Dragon" is a track from Vangelis's 1979 electronic music album "China," blending synthesizer-driven soundscapes with an evocative, atmospheric style.
-
D.
The Dragon
The Dragon is a renowned martial arts school known for its rigorous training and emphasis on traditional fighting techniques.
-
E.
Drakonera
Drakonera is a notable Greek island in the Ionian Sea, forming part of the Echinades archipelago off the western coast of mainland Greece.
- 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_69d6aa9eb9248190b20211772621b4bc |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e8af18e4819091811bca657c9cb0 |
completed | April 9, 2026, 5:58 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e483ec6ca8819082713a278c987756 |
completed | April 19, 2026, 7:27 a.m. |
| NEDg | Description generation | batch_69e48788be688190a109ccb8281d3dc9 |
completed | April 19, 2026, 7:43 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69e4890c12388190838d350207492c9e |
completed | April 19, 2026, 7:49 a.m. |
Created at: April 8, 2026, 9:29 p.m.