Triple
T6143413
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Orange S.A. |
E137016
|
entity |
| Predicate | stockIndex |
P10508
|
FINISHED |
| Object | CAC 40 |
E23686
|
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: CAC 40 | Statement: [Orange S.A., stockIndex, CAC 40]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CAC 40 Context triple: [Orange S.A., stockIndex, CAC 40]
-
A.
CAC 40
chosen
CAC 40 is the benchmark French stock market index, tracking 40 major companies listed on the Euronext Paris exchange.
-
B.
Swiss Market Index
The Swiss Market Index is Switzerland’s leading stock market benchmark, comprising the largest and most liquid blue-chip companies traded on the SIX Swiss Exchange.
-
C.
S&P Europe 350
S&P Europe 350 is a major stock market index that tracks the performance of 350 leading blue-chip companies across developed European markets.
-
D.
Euro Stoxx 50
The Euro Stoxx 50 is a leading blue-chip stock market index that tracks the performance of 50 major companies from countries within the eurozone.
-
E.
FTSE All-World Index
The FTSE All-World Index is a broad global equity benchmark that tracks the performance of large- and mid-cap stocks across both developed and emerging markets worldwide.
- 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_69c008a2c6308190a56519b22d55d083 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c05cb50cb0819081ac64becf7aaf55 |
completed | March 22, 2026, 9:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c640a09c60819087f3dad6d6ac6833 |
completed | March 27, 2026, 8:32 a.m. |
Created at: March 22, 2026, 4:16 p.m.