Triple
T8248401
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hydra |
E192900
|
entity |
| Predicate | supportsProtocol |
P203
|
FINISHED |
| Object |
Firebird
Firebird is an open-source relational database management system known for its support of SQL and cross-platform deployment.
|
E721434
|
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: Firebird | Statement: [Hydra, supportsProtocol, Firebird]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Firebird Context triple: [Hydra, supportsProtocol, Firebird]
-
A.
Firebird
Firebird is a floorless steel roller coaster at Six Flags America known for its inversions and smooth, high-speed ride experience.
-
B.
Firebird
Firebird is the fiery, mythical bird mascot representing Fremont High School in Sunnyvale, California, symbolizing resilience and school spirit.
-
C.
Firebird
Firebird is a celebrated ballet role, famously performed by Maria Tallchief in Igor Stravinsky’s classic work "The Firebird."
-
D.
Cocoon
Cocoon is a 1985 science fiction comedy-drama film about a group of elderly people who regain youth and vitality after encountering alien life, directed by Ron Howard.
-
E.
Cocoon
Cocoon is an acclaimed indie puzzle-adventure video game known for its innovative world-within-worlds mechanic and atmospheric, wordless storytelling.
- 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: Firebird Triple: [Hydra, supportsProtocol, Firebird]
Generated description
Firebird is an open-source relational database management system known for its support of SQL and cross-platform deployment.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Firebird Target entity description: Firebird is an open-source relational database management system known for its support of SQL and cross-platform deployment.
-
A.
Firebird
Firebird is a floorless steel roller coaster at Six Flags America known for its inversions and smooth, high-speed ride experience.
-
B.
Firebird
Firebird is a celebrated ballet role, famously performed by Maria Tallchief in Igor Stravinsky’s classic work "The Firebird."
-
C.
Firebird
Firebird is the fiery, mythical bird mascot representing Fremont High School in Sunnyvale, California, symbolizing resilience and school spirit.
-
D.
Cocoon
Cocoon is a 1985 science fiction comedy-drama film about a group of elderly people who regain youth and vitality after encountering alien life, directed by Ron Howard.
-
E.
Cocoon
Cocoon is an acclaimed indie puzzle-adventure video game known for its innovative world-within-worlds mechanic and atmospheric, wordless storytelling.
- 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_69ca82de7b8c81908d8106f8a53cff9b |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb78c6b3c48190a3ecebf449766124 |
completed | March 31, 2026, 7:33 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cd3530ca148190a28761622d0cf663 |
completed | April 1, 2026, 3:09 p.m. |
| NEDg | Description generation | batch_69cd37a71af481909e82aa29ae558c4a |
completed | April 1, 2026, 3:20 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69cd4ef034ec8190a4229b21e6088c79 |
completed | April 1, 2026, 4:59 p.m. |
Created at: March 30, 2026, 5:48 p.m.