Triple
T18021215
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Superior vena cava |
E431119
|
entity |
| Predicate | hasAbbreviation |
P43
|
FINISHED |
| Object |
SVC
SVC is a major vein in the upper chest that returns deoxygenated blood from the head, neck, upper limbs, and upper torso to the right atrium of the heart.
|
E1301605
|
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: SVC | Statement: [Superior vena cava, hasAbbreviation, SVC]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SVC Context triple: [Superior vena cava, hasAbbreviation, SVC]
-
A.
SVC
SVC is scikit-learn’s implementation of a Support Vector Machine classifier used for supervised learning tasks such as binary and multiclass classification.
-
B.
SVC
SVC is the commonly used abbreviation for Sri Venkateswara Creations, a prominent Indian film production company known for producing Telugu-language movies.
-
C.
SAVC
SAVC is the ICAO airport code for General Enrique Mosconi International Airport in Comodoro Rivadavia, Argentina.
-
D.
SVCN
SVCN is the ICAO airport code for Canaima airstrip, a small airport serving the Canaima National Park region in Venezuela.
-
E.
svcs
svcs is a Solaris command-line utility that displays the status and detailed information of services managed by the Service Management Facility (SMF).
- 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: SVC Triple: [Superior vena cava, hasAbbreviation, SVC]
Generated description
SVC is a major vein in the upper chest that returns deoxygenated blood from the head, neck, upper limbs, and upper torso to the right atrium of the heart.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: SVC Target entity description: SVC is a major vein in the upper chest that returns deoxygenated blood from the head, neck, upper limbs, and upper torso to the right atrium of the heart.
-
A.
SVC
SVC is scikit-learn’s implementation of a Support Vector Machine classifier used for supervised learning tasks such as binary and multiclass classification.
-
B.
SVC
SVC is the commonly used abbreviation for Sri Venkateswara Creations, a prominent Indian film production company known for producing Telugu-language movies.
-
C.
SAVC
SAVC is the ICAO airport code for General Enrique Mosconi International Airport in Comodoro Rivadavia, Argentina.
-
D.
SVCN
SVCN is the ICAO airport code for Canaima airstrip, a small airport serving the Canaima National Park region in Venezuela.
-
E.
svcs
svcs is a Solaris command-line utility that displays the status and detailed information of services managed by the Service Management Facility (SMF).
- 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_69d8b904530081908bf341d842464856 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4b9c299c48190b0cceecf77cb6de9 |
completed | April 19, 2026, 11:17 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a034328fef08190a3f78f8bee859d24 |
completed | May 12, 2026, 3:11 p.m. |
| NEDg | Description generation | batch_6a03447c0530819082d554592eec03ca |
completed | May 12, 2026, 3:17 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a034552e424819087b23bcf3f688523 |
completed | May 12, 2026, 3:20 p.m. |
Created at: April 10, 2026, 10:24 a.m.