Triple
T37309091
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Recinto Expo Zaragoza |
E926155
|
entity |
| Predicate | themeOfHostedExpo |
P112320
|
FINISHED |
| Object | Water and Sustainable Development |
—
|
NE NERFINISHED |
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: Water and Sustainable Development | Statement: [Recinto Expo Zaragoza, themeOfHostedExpo, Water and Sustainable Development]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: themeOfHostedExpo Context triple: [Recinto Expo Zaragoza, themeOfHostedExpo, Water and Sustainable Development]
-
A.
exhibitTheme
Indicates that something (such as a work, event, or presentation) presents, embodies, or is organized around a particular theme.
-
B.
eventTheme
chosen
Indicates that an entity serves as the central subject, topic, or thematic focus of an event.
-
C.
themeExplores
Indicates that a work, action, or discourse centrally examines, investigates, or delves into a particular theme or subject.
-
D.
operatorDuringExpo
Indicates that an entity serves as an operator specifically during an exposition or expo event.
-
E.
expoSite
Indicates that a site or location is designated as the venue or setting for an exposition or exhibition event.
- 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_69f76eb1bc508190924e9fa5d8acdeb3 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb78cbef988190b8f79d946b46e6b2 |
completed | May 6, 2026, 5:22 p.m. |
| PD | Predicate disambiguation | batch_69fb5a9ac5a08190b24ef308963fc52b |
completed | May 6, 2026, 3:13 p.m. |
Created at: May 3, 2026, 4:16 p.m.