Triple
T19792316
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Māngere |
E475444
|
entity |
| Predicate | hasNeighbour |
P5707
|
FINISHED |
| Object |
Favona
Favona is a residential and industrial suburb in South Auckland, New Zealand, located near Māngere and the Manukau Harbour.
|
E1395264
|
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: Favona | Statement: [Māngere, hasNeighbour, Favona]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Favona Context triple: [Māngere, hasNeighbour, Favona]
-
A.
Farinola
Farinola is an Italian surname, notably borne by American traditional pop and big band singer Vic Damone, who was born Vito Rocco Farinola.
-
B.
Faventia
Faventia is the ancient Roman name for the Italian city of Faenza, historically known as an important settlement in northern Italy.
-
C.
Faeto
Faeto is a small town in southern Italy known for its unique linguistic heritage, including the rare Franco-Provençal dialect Faetar.
-
D.
Fossanova
Fossanova is a locality in central Italy known for giving its name to the nearby medieval Cistercian monastery, Fossanova Abbey.
-
E.
Ferrandina
Ferrandina is a historic hill town and comune in the Basilicata region of southern Italy, known for its olive oil production and characteristic whitewashed houses.
- 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: Favona Triple: [Māngere, hasNeighbour, Favona]
Generated description
Favona is a residential and industrial suburb in South Auckland, New Zealand, located near Māngere and the Manukau Harbour.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Favona Target entity description: Favona is a residential and industrial suburb in South Auckland, New Zealand, located near Māngere and the Manukau Harbour.
-
A.
Farinola
Farinola is an Italian surname, notably borne by American traditional pop and big band singer Vic Damone, who was born Vito Rocco Farinola.
-
B.
Faventia
Faventia is the ancient Roman name for the Italian city of Faenza, historically known as an important settlement in northern Italy.
-
C.
Faeto
Faeto is a small town in southern Italy known for its unique linguistic heritage, including the rare Franco-Provençal dialect Faetar.
-
D.
Fossanova
Fossanova is a locality in central Italy known for giving its name to the nearby medieval Cistercian monastery, Fossanova Abbey.
-
E.
Ferrandina
Ferrandina is a historic hill town and comune in the Basilicata region of southern Italy, known for its olive oil production and characteristic whitewashed houses.
- 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_69d8e51b014081908b263e167370529a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e653c37a3c819080f195d58adaaa7b |
completed | April 20, 2026, 4:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a07c4fff3548190a069b665c0885627 |
completed | May 16, 2026, 1:14 a.m. |
| NEDg | Description generation | batch_6a07c580b3108190bcc64fe1f479d7c4 |
completed | May 16, 2026, 1:16 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a07c5e7a5d08190b6a24f66ff966cec |
completed | May 16, 2026, 1:18 a.m. |
Created at: April 10, 2026, 1:49 p.m.