Triple
T21183852
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Racibórz |
E522024
|
entity |
| Predicate | vehicleRegistrationCode |
P1173
|
FINISHED |
| Object |
SRC
SRC is the vehicle registration code assigned to cars registered in Racibórz, a town in southern Poland.
|
E1470070
|
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: SRC | Statement: [Racibórz, vehicleRegistrationCode, SRC]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SRC Context triple: [Racibórz, vehicleRegistrationCode, SRC]
-
A.
SRC
SRC is a Canadian French-language television network owned by the Canadian Broadcasting Corporation, serving as its primary public broadcasting service in French.
-
B.
SRC
SRC is the station code for Santragachi Junction, a major railway station serving the Howrah–Kolkata area in West Bengal, India.
-
C.
SRC
SRC (System Resource Controller) is a system management component used in some Unix-like operating systems to start, stop, and control system services and daemons.
-
D.
Source
Source is Valve Corporation’s proprietary 3D game engine known for powering titles like Half-Life 2, Portal, and Team Fortress 2, featuring advanced physics, facial animation, and mod support.
-
E.
SCR
SCR at St Chad’s College refers to the Senior Common Room, the community and social/academic body of the college’s senior members, including fellows and staff.
- 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: SRC Triple: [Racibórz, vehicleRegistrationCode, SRC]
Generated description
SRC is the vehicle registration code assigned to cars registered in Racibórz, a town in southern Poland.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: SRC Target entity description: SRC is the vehicle registration code assigned to cars registered in Racibórz, a town in southern Poland.
-
A.
SRC
SRC is a Canadian French-language television network owned by the Canadian Broadcasting Corporation, serving as its primary public broadcasting service in French.
-
B.
SRC
SRC is the station code for Santragachi Junction, a major railway station serving the Howrah–Kolkata area in West Bengal, India.
-
C.
SRC
SRC (System Resource Controller) is a system management component used in some Unix-like operating systems to start, stop, and control system services and daemons.
-
D.
Source
Source is Valve Corporation’s proprietary 3D game engine known for powering titles like Half-Life 2, Portal, and Team Fortress 2, featuring advanced physics, facial animation, and mod support.
-
E.
SCR
SCR at St Chad’s College refers to the Senior Common Room, the community and social/academic body of the college’s senior members, including fellows and staff.
- 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_69e0b50ef1d48190b063aa342667df22 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7301f7f1c81908686866fdee57127 |
completed | April 21, 2026, 8:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09757d659881909e41f593417247e5 |
completed | May 17, 2026, 7:59 a.m. |
| NEDg | Description generation | batch_6a09769c4d1c8190bf8f53fafc840fa9 |
completed | May 17, 2026, 8:04 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a097709a4c88190a38d787260599348 |
completed | May 17, 2026, 8:06 a.m. |
Created at: April 16, 2026, 3:05 p.m.