Triple
T7474619
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lake Constance |
E176598
|
entity |
| Predicate | bordersCity |
P224
|
FINISHED |
| Object |
Rorschach
Rorschach is a Swiss lakeside town in the canton of St. Gallen, known for its historic harbor and location on the southern shore of Lake Constance.
|
E667595
|
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: Rorschach | Statement: [Lake Constance, bordersCity, Rorschach]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rorschach Context triple: [Lake Constance, bordersCity, Rorschach]
-
A.
Rorschach
Rorschach is a masked vigilante antihero from the Watchmen universe, known for his uncompromising moral absolutism and inkblot-patterned mask.
-
B.
The Man
The Man is a film featuring actor Richard Gant in a significant role.
-
C.
The Man
"The Man" is a 2017 funk-influenced rock single by American band The Killers, known for its swaggering, self-confident lyrics and bold, retro sound.
-
D.
The Man
The Man is a poem by Russian Futurist poet Vladimir Mayakovsky that explores themes of individuality, alienation, and modern urban life in his characteristically bold, experimental style.
-
E.
Rothstein
Rothstein is a Germanic-origin surname notably borne by individuals such as American photographer Arthur Rothstein.
- 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: Rorschach Triple: [Lake Constance, bordersCity, Rorschach]
Generated description
Rorschach is a Swiss lakeside town in the canton of St. Gallen, known for its historic harbor and location on the southern shore of Lake Constance.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Rorschach Target entity description: Rorschach is a Swiss lakeside town in the canton of St. Gallen, known for its historic harbor and location on the southern shore of Lake Constance.
-
A.
Rorschach
Rorschach is a masked vigilante antihero from the Watchmen universe, known for his uncompromising moral absolutism and inkblot-patterned mask.
-
B.
The Man
The Man is a film featuring actor Richard Gant in a significant role.
-
C.
The Man
"The Man" is a 2017 funk-influenced rock single by American band The Killers, known for its swaggering, self-confident lyrics and bold, retro sound.
-
D.
The Man
The Man is a poem by Russian Futurist poet Vladimir Mayakovsky that explores themes of individuality, alienation, and modern urban life in his characteristically bold, experimental style.
-
E.
Rothstein
Rothstein is a Germanic-origin surname notably borne by individuals such as American photographer Arthur Rothstein.
- 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_69c69f236ce08190a04d7679f03b29b2 |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f417fbb48190b134eaf1da1b4289 |
completed | March 27, 2026, 9:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8348561448190add358da0845fbee |
completed | March 28, 2026, 8:05 p.m. |
| NEDg | Description generation | batch_69c83544c524819094d013affc03ff62 |
completed | March 28, 2026, 8:08 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c835ea13c88190b7423c6c7bdae983 |
completed | March 28, 2026, 8:11 p.m. |
Created at: March 27, 2026, 3:41 p.m.