Triple
T15229220
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Albert |
E363953
|
entity |
| Predicate | roadConnection |
P385
|
FINISHED |
| Object |
D938 road
The D938 road is a departmental highway in France that serves as a regional connector between various towns and localities.
|
E1145942
|
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: D938 road | Statement: [Albert, roadConnection, D938 road]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: D938 road Context triple: [Albert, roadConnection, D938 road]
-
A.
D93 road
D93 road is a regional roadway that provides access to the village of Die in southeastern France, connecting it to the surrounding Drôme area.
-
B.
D983 road
The D983 road is a regional route in central France that provides access to the scenic Lac de Guéry in the Massif Central.
-
C.
D932 road
The D932 road is a departmental highway in northern France that connects several communes, including Bohain-en-Vermandois, and serves as a regional transport route.
-
D.
D988 road
The D988 road is a regional route in southern France that connects the town of Langogne with other nearby localities in the Lozère area.
-
E.
D989 road
The D989 road is a regional route in northeastern France that provides access to the town of Monthermé and connects it with other nearby localities.
- 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: D938 road Triple: [Albert, roadConnection, D938 road]
Generated description
The D938 road is a departmental highway in France that serves as a regional connector between various towns and localities.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: D938 road Target entity description: The D938 road is a departmental highway in France that serves as a regional connector between various towns and localities.
-
A.
D93 road
D93 road is a regional roadway that provides access to the village of Die in southeastern France, connecting it to the surrounding Drôme area.
-
B.
D983 road
The D983 road is a regional route in central France that provides access to the scenic Lac de Guéry in the Massif Central.
-
C.
D932 road
The D932 road is a departmental highway in northern France that connects several communes, including Bohain-en-Vermandois, and serves as a regional transport route.
-
D.
D988 road
The D988 road is a regional route in southern France that connects the town of Langogne with other nearby localities in the Lozère area.
-
E.
D989 road
The D989 road is a regional route in northeastern France that provides access to the town of Monthermé and connects it with other nearby localities.
- 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_69d85a0ce24c81909c4d3b6475548c95 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e0078ccdf48190b34eabd9e24e45a1 |
completed | April 15, 2026, 9:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fee5edca5c8190827788324a9e886d |
completed | May 9, 2026, 7:44 a.m. |
| NEDg | Description generation | batch_69fee6706764819099ad22a6289ac465 |
completed | May 9, 2026, 7:46 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69fee706214081909468535055497b8f |
completed | May 9, 2026, 7:49 a.m. |
Created at: April 10, 2026, 3:12 a.m.