Triple
T37643534
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | PSE |
E936673
|
entity |
| Predicate | formerTradingFloorLocation |
P197701
|
FINISHED |
| Object | Makati, Metro Manila, Philippines |
—
|
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: Makati, Metro Manila, Philippines | Statement: [PSE, formerTradingFloorLocation, Makati, Metro Manila, Philippines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerTradingFloorLocation Context triple: [PSE, formerTradingFloorLocation, Makati, Metro Manila, Philippines]
-
A.
hasTradingFloorFor
Indicates that one entity operates or provides a trading floor facility used for conducting trading activities related to another entity.
-
B.
formerLocationNow
chosen
Indicates that an entity used to be located at a place in the past but is no longer located there now.
-
C.
formerlyLocatedOn
Indicates that an entity was once located on or situated upon another entity, but is no longer in that position.
-
D.
headquartersPreviousLocation
Indicates that an entity’s headquarters used to be located at a specified place before moving to its current location.
-
E.
hasTradingFloor
Indicates that an entity operates or contains a physical or virtual trading floor where financial instruments are actively bought and sold.
- 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_69f76ed31d8881908405da6c6d2f0463 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a0119132e848190820a688d139fbf75 |
completed | May 10, 2026, 11:47 p.m. |
| PD | Predicate disambiguation | batch_6a01188dfdec8190b7f675264a281733 |
completed | May 10, 2026, 11:45 p.m. |
Created at: May 3, 2026, 4:18 p.m.