Triple
T32345043
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Le Havre |
E826433
|
entity |
| Predicate | portRankInFranceByTraffic |
P15147
|
FINISHED |
| Object | among largest |
—
|
LITERAL FINISHED |
How this triple was built (2 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: among largest | Statement: [Le Havre, portRankInFranceByTraffic, among largest]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: portRankInFranceByTraffic Context triple: [Le Havre, portRankInFranceByTraffic, among largest]
-
A.
populationRankInFrance
Indicates the relative position of an entity in an ordered list based on its population size within France.
-
B.
airportRankInFranceByTraffic
Indicates the relative position of an airport in France when airports are ordered by the volume of passenger or cargo traffic they handle.
-
C.
cargoTrafficRankInFrance
chosen
Indicates the ranking position of an entity based on the volume of cargo traffic it handles within France.
-
D.
collectionRankInFrance
Indicates the position or level of a collection within a ranking specific to France.
-
E.
economicRankInFrance
Indicates the relative economic standing or ranking of an entity within the context of France’s economy.
- F. None of above.
Provenance (3 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_69f34914dfc48190a390cd0720d9e86f |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fe59d11e9881909d2f33b7c717030e |
completed | May 8, 2026, 9:46 p.m. |
| PD | Predicate disambiguation | batch_69fe394fdfbc8190a931926ae3635cbf |
completed | May 8, 2026, 7:28 p.m. |
Created at: May 1, 2026, 12:48 a.m.