Triple
T10237476
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Royal Dutch Shell |
E243501
|
entity |
| Predicate | memberOf |
P10
|
FINISHED |
| Object | AEX Index |
E3962
|
NE 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: AEX Index | Statement: [Royal Dutch Shell, memberOf, AEX Index]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: AEX Index Context triple: [Royal Dutch Shell, memberOf, AEX Index]
-
A.
AEX index
chosen
The AEX index is a benchmark stock market index that tracks the performance of the largest and most actively traded companies listed on the Amsterdam Stock Exchange.
-
B.
Amsterdam Small Cap Index
The Amsterdam Small Cap Index (AScX) is a Dutch stock market index that tracks the performance of smaller, publicly traded companies listed on Euronext Amsterdam.
-
C.
SDAX
SDAX is a German stock market index that tracks the performance of small-cap companies listed on the Frankfurt Stock Exchange.
-
D.
IDX30 Index
IDX30 Index is a stock market index on the Indonesia Stock Exchange that tracks the performance of 30 of its most liquid and large-cap listed companies.
-
E.
IBEX 35
IBEX 35 is Spain’s benchmark stock market index, comprising the 35 most liquid and highly capitalized companies traded on the Bolsa de Madrid.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d381b0f97c819085c9b45799a5fb7c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d21b64c88190b708c20ca7fe20aa |
completed | April 7, 2026, 9:44 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d6f76ca8848190a49d7dc76cf9dd35 |
completed | April 9, 2026, 12:48 a.m. |
Created at: April 6, 2026, 11:23 a.m.